LSEG

Execute Datastream DSWS GetData queries and return normalized tabular results. Request must include at least one entry in the requests array. Each entry can be either a standard instruments + fields request or an expression-only request. INSTRUMENT IDENTIFIER RULES: - RICs (Reuters Instrument Codes) must be enclosed in angle brackets, e.g. "<SHEL.L>", "<MSFT.O>", "<IBM.N>". IMPORTANT: Only equity-style RICs with exchange suffixes (.L, .N, .O, .A) are supported in brackets. Currency RICs like <EUR=>, <GBP=>, <JPY=> are NOT supported. Use the 6-letter pair instead (e.g. EURUSD, GBPUSD). - Datastream mnemonics (e.g. 'MSFT', 'VOD', '@AAPL') are passed directly without brackets. - FX/Currency pairs: if you know the exact Datastream mnemonic (e.g. TEUSDSP for EUR/USD), use it directly. Otherwise, pass a 6-letter currency pair (e.g. EURUSD, GBPUSD, USDJPY) and it will be auto-resolved to the correct Datastream mnemonic via navigator/search. You can also use datastream_search with category="Fx" first to find the exact mnemonic yourself. - Economics mnemonics: pass as-is including dot notation (e.g. USGDP...B, USGDP...D). - Instruments that look like a mnemonic or RIC will be passed to the Datastream data endpoint as-is. - If the instrument does not look like a known mnemonic or RIC, it will be resolved using the navigator/search API endpoint automatically. - If the response contains an error or returns data for an incorrect mnemonic, use the datastream_search tool first to find the correct mnemonic code, then call this data endpoint again with the resolved mnemonic. FIELD/DATATYPE RULES: - X is the universal default datatype for ANY instrument category in Timeseries mode. If unsure which field to use for timeseries, use X. Note: X does NOT work for Snapshot requests. - For Snapshots, you MUST specify the correct category-specific field: * Equities/Indices: P (price), MV (market value), PE (price-to-earnings) * FX/Exchange Rates: ER (exchange rate) * Economics: ES (economic series value) - INVALID fields that will always return NA or error: BID, ASK, DS, VALUE, CLOSE. These are NOT valid Datastream datatypes for any category. - When in doubt about which field to use, call datastream_search with requestType='Fields' and the appropriate category. EXPRESSION RULES: - Use the expression field when you already have the final Datastream expression string, e.g. "PCH#(VOD,-1M)" or "300E(MKS,12M)". - Do not combine expression with instruments or fields. The expression string contains the executable calculation. - Dynamic expressions call Datastream functions directly, e.g. "PCH#(VOD,-1M)". - Pre-built expressions use a discovered expression mnemonic/code with arguments, e.g. "300E(MKS,12M)" after finding 300E via datastream_search requestType="Expressions". - Expression parameter metadata is limited. Instrument arguments are usually Datastream mnemonics such as MKS, VOD, or @AAPL; period/window arguments commonly use Datastream-compatible values such as 12M, -1M, -20D, or -1Y; numeric arguments are plain numbers. - If parameter meaning is unclear, pass the final expression string as provided and let DSWS validate semantics. TWO KINDS AND HOW TO USE THEM: 1. Snapshot - Use for a single point-in-time value per instrument/field. - Best for current values or latest available observations. - Typical payload: instruments + fields + kind="Snapshot". - MUST use category-specific field (P, ER, ES). X does NOT work for Snapshots. 2. Timeseries - Use for values across a date range. - Best for trend analysis, charting, and period-over-period comparisons. - Typical payload: instruments + fields + kind="Timeseries" with optional start/end/frequency. - Can use X as universal default field for any category. EXAMPLE REQUEST PAYLOAD: { "requests": [ { "instruments": "MSFT, <SHEL.L>", "fields": "MV, PE", "start": "-1Y", "end": "0D", "frequency": "Monthly", "kind": "Timeseries" }, { "instruments": "@AAPL", "fields": "P", "kind": "Snapshot" }, { "instruments": "EURUSD", "fields": "X", "start": "-1M", "end": "0D", "frequency": "Daily", "kind": "Timeseries" }, { "instruments": "USGDP...B", "fields": "X", "start": "-3Y", "end": "0D", "frequency": "Quarterly", "kind": "Timeseries" }, { "expression": "PCH#(VOD,-1M)", "start": "-1Y", "end": "0D", "frequency": "Monthly", "kind": "Timeseries" }, { "expression": "300E(MKS,12M)", "start": "-1Y", "end": "0D", "frequency": "Daily", "kind": "Timeseries" } ] }

datastream_data

Search Datastream Navigator/Search API to discover instruments, field/datatype codes, or pre-built expressions before retrieving data. Each request entry must specify a requestType of "Instruments", "Fields", or "Expressions" to indicate the type of search being performed. TIPS: - Use category filter to narrow results (e.g. "Fx" for exchange rates, "Economics" for GDP/CPI series). - Use requestType="Fields" to discover valid datatypes for a category before requesting data. - Use requestType="Expressions" to discover pre-built expressions by name, mnemonic/code, formula terms, or parameter names. - Expression search can help build executable expressions for datastream_data, e.g. a discovered expression mnemonic can be called as "300E(MKS,12M)". - Expression parameters currently have limited metadata. Instrument arguments are usually Datastream mnemonics such as MKS or VOD; period/window arguments commonly use Datastream-compatible values such as 12M, -1M, -20D, or -1Y. DSWS validates final expression semantics. - Common categories: Equities, Fx, Economics, Bonds, Commodities, EquityIndices, Funds, InterestRates. EXAMPLE REQUEST PAYLOAD: { "requests": [ { "requestType": "Instruments", "query": "Vodafone", "category": "Equities", "maxResults": 15 }, { "requestType": "Instruments", "query": "EURUSD", "category": "Fx", "maxResults": 5 }, { "requestType": "Instruments", "query": "United States GDP", "category": "Economics", "maxResults": 10 }, { "requestType": "Fields", "query": "price", "category": "Equities", "limit": 20, "offset": 0, "timeseriesOnly": false, "currencyEnabled": false }, { "requestType": "Expressions", "query": "z-score normalization", "limit": 10, "offset": 0 } ] }

datastream_search

**BEFORE CALLING: Count identifiers first. MAX 5 IDENTIFIERS PER CALL.** If user has >5 bonds, split into multiple calls BEFORE executing (e.g., 12 bonds = 3 calls: 5 + 5 + 2). Retrieve actual vs projected prepayment data for mortgage-backed securities via YieldBook API. Compares historical actual prepayment speeds against model-projected speeds. This tool is only for backward looking historical analysis of actual vs projected prepayment. Do not use this tool for forward-looking analysis. If the user asks to run a PY, requests forward-looking/prepayment projections, use fixed_income_risk_analytics instead. REQUIRED PARAMETER: - identifiers: Array of up to 5 bond identifiers (CUSIP, ISIN, or YieldBook ID). FNMA or GNMA or similar IDENTIFIER FORMAT: If a user provides space-separated notation like FNMA11.100 F or FNMA20.100 BA, change it to FNMA11.100(F) or FNMA20.100(BA) by replacing the space with parenthesis automatically. If FNMA200.100 or similar id is provided without any letter, pass it as is (no parentheses needed). If ticket has # like N25.1(#1), pass as is. OPTIONAL PARAMETER: - idType: type of identifier provided (e.g., "CUSIP", "ISIN", "SecurityIDEntry", etc.). Defaults to "SecurityIDEntry" if not specified. - prepayType: MBS prepayment model to use. Defaults to "Model" if not specified. Accepted values: - "Model" — current production model (default) - "ExpModel" - Model 99 - "NewModel" - "OldExpModel" - "OldModel" - "PreExpModel" — Model 97 Only one prepayType is accepted per call. RETURNED INFORMATION: - Identity fields: CUSIP, ISIN, ticker, description, security type, maturity date, current coupon - Monthly actual vs projected CPR vector (dataActVsProjVectorList): date, actualCPR, actualCDR, projectedCPR, projectedCDR, projectedVPR, projectedRefi, projectedCurtail, projectedTurnover - Period summaries (dataActVsProjSummaryList): 1-month, 3-month, 6-month, 12-month, 24-month, and Life aggregates USE CASES: 1. **Historical prepayment analysis**: View actual CPR/CDR history for MBS pools 2. **Historical projected prepayment speed**: Get model-projected CPR, VPR, refinancing, curtailment, and turnover rates that are returned alongside historical actual observations 3. **Actual vs projected comparison**: Compare realized prepayment speeds against YieldBook model projections to assess model accuracy SUPPORTED SECURITY TYPES: - Mortgage-backed securities (MBS, RMBS) - Collateralized mortgage obligations (CMO) - Agency pass-throughs (FNMA, GNMA, FHLMC) KEY FEATURES: - Batch support: Query up to 5 identifiers per request - Multiple identifier types: CUSIP, ISIN, generic YieldBook IDs. If user provides multiple identifiers of different types (e.g., one CUSIP and one ISIN), split into separate calls to the tool. - Decomposed projections: See refi, curtailment, and turnover components separately DEFAULT: If idType not specified, defaults to 'SecurityIDEntry'. If prepayType not specified, defaults to 'Model'. IDTYPE NOTE: If user provides multiple identifiers of different types (e.g., one CUSIP and one ISIN), split into separate calls to the tool since only one idType is accepted at a time. PREPAYTYPE NOTE: Only one prepayType is accepted per call. To compare models or use different models for different groups of identifiers, split into separate calls to the tool. ASYNC STATUS CHECK: If a previous request was still processing (returned jobRef and requestId), call this same tool with only { "jobRef": "...", "requestId": "..." } to check if results are ready. EXAMPLE - "Give me the past six months of historical prepayments on security <identifier>" {"identifiers": ["<identifier>"], "idType": "SecurityIDEntry", "prepayType": "Model"} EXAMPLE - "Show historical speeds on <identifier 1>, <identifier 2>, and <identifier 3>" {"identifiers": ["<identifier 1>", "<identifier 2>", "<identifier 3>"], "idType": "SecurityIDEntry", "prepayType": "Model"} EXAMPLE - "Give me the past six months of Yield Book projected CPRs on CUSIP <identifier>" {"identifiers": ["<identifier>"], "idType": "CUSIP", "prepayType": "Model"} EXAMPLE - "Compare historical speeds versus Yield Book Projected speeds on <identifier>" {"identifiers": ["<identifier>"], "idType": "SecurityIDEntry", "prepayType": "Model"} EXAMPLE - "Run Yield Book Actual vs Projected on <identifier 1>, <identifier 2>, <identifier 3>, and <identifier 4>" {"identifiers": ["<identifier 1>", "<identifier 2>", "<identifier 3>", "<identifier 4>"], "idType": "SecurityIDEntry", "prepayType": "Model"} EXAMPLE - "How did Yield Book projected CPRs compare to historical CPRs on <identifier>" {"identifiers": ["<identifier>"], "idType": "SecurityIDEntry", "prepayType": "Model"} EXAMPLE - "Run actual vs projected using Model 99 on <identifier>" {"identifiers": ["<identifier>"], "idType": "SecurityIDEntry", "prepayType": "ExpModel"} EXAMPLE - "Compare Model 97 projected speeds against actuals on <identifier>" {"identifiers": ["<identifier>"], "idType": "SecurityIDEntry", "prepayType": "PreExpModel"} EXAMPLE - "Run Yieldbook Actual vs Projected for jobRef <jobRef> and requestId <requestId>" {"jobRef": "<jobRef>", "requestId": "<requestId>"}

fixed_income_actual_vs_projected

**BEFORE CALLING: Count identifiers first. MAX 50 IDENTIFIERS PER CALL.** If user has >50 bonds, split into multiple calls BEFORE executing (e.g., 75 bonds = 2 calls: 50 + 25). Do NOT attempt >50 identifiers - it will fail. Retrieve bond reference data via YieldBook Bond Indic API. Returns contractual and reference information about bonds without requiring calculations. RETURNED INFORMATION: - Security type and sector classification - Maturity date and coupon details - Credit ratings (S&P, Moody's, Fitch) - Issuer information and CUSIP/ISIN identifiers - Security-specific data (e.g., pool factor for MBS) - Payment frequency and day count conventions SUPPORTED SECURITY TYPES: - Government bonds (Treasury, Agency) - Corporate bonds - Mortgage-backed securities or similar ties(MBS, RMBS, CMBS) - Asset-backed securities (ABS) - Municipal bonds - Collateralized mortgage obligations (CMO) KEY FEATURES: - Batch support: Query up to 50 identifiers per request - Multiple identifier types: CUSIP, ISIN, generic YieldBook IDs - FNMA or GNMA or similar IDENTIFIER FORMAT: If a user provides space-separated notation like FNMA11.100 F or FNMA20.100 BA, change it to FNMA11.100(F) or FNMA20.100(BA) by replacing the space with parenthesis automatically. If FNMA200.100 or similar id is provided without any letter, pass it as is. If ticket has # like N25.1(#1), pass as is. - Optional keyword filtering to retrieve specific fields only - No calculations required - pure reference data lookup USE CASES: - Bond identification and basic information lookup - Security screening and filtering - Portfolio composition analysis - Credit rating verification DEFAULT: If idType not specified, defaults to 'CUSIP'. ASYNC STATUS CHECK: If a previous request was still processing (returned jobRef and requestId), call this same tool with only { "jobRef": "...", "requestId": "..." } to check if results are ready. Do not include identifiers or other parameters when checking status.

fixed_income_bond_reference

**BEFORE CALLING: Count bonds first. MAX 10 BONDS PER CALL.** If user has >10 bonds, split into multiple calls BEFORE executing (e.g., 25 bonds = 3 calls: 10 + 10 + 5). Do NOT attempt >10 bonds - it will fail. Calculate bond cashflow schedules via YieldBook Cashflow API. Returns payment dates, principal, interest, and prepayment projections for Fixed rate, MBS/RMBS/CMBS, CMO, FRN, Municipal, Agency securities. For MBS/ABS bonds, include the prepay type and rate used in the output (e.g., "Running with Model 100" or "Running with CPR 6"). This is not applicable to corporate or government bonds. MBS/TBA/CMO PREPAY DEFAULTS — ALWAYS INCLUDE for mortgage-backed securities: When requesting cashflows for MBS, TBA, CMO, or ABS bonds, you MUST include prepay settings with BOTH type AND rate: - Default: prepay: {"type": "Model", "rate": 100} — runs the YieldBook prepay model at 100% of projected speed. - Omitting rate causes a "PrepayRate not specified" error. Always include both type AND rate together. PREPAY MODEL VERSIONS (updated annually): Model/CurrentModel/NewModel=25.1, OldModel=24.1, PreExpModel=97, ExpModel=99. For rate types: CPR (e.g., 6=6% CPR), PSA (e.g., 150=150% PSA). REQUIRED PARAMETERS (per bond): - identifier: Bond ID (CUSIP, ISIN, or YieldBook ID). FNMA or GNMA or similarIDENTIFIER FORMAT: If a user provides space-separated notation like FNMA11.100 F or FNMA20.100 BA, change it to FNMA11.100(F) or FNMA20.100(BA) by replacing the space with parenthesis automatically. If FNMA200.100 or similar id is provided without any letter, pass it as is (no parentheses needed). If ticket has # like N25.1(#1), pass as is. OPTIONAL PARAMETERS (per bond): - idType, parAmount, settlementType, settlementDate, curve {curveType, currency, retrieveCurve}, prepay {type, rate}, floaterSettings {useForwardIndex}, userTag GLOBAL SETTINGS - ALWAYS INCLUDE in every request: - globalSettings is REQUIRED. Always send globalSettings with a date option. If user does not specify, default to { usePreviousClose: true }. - keywords: Array of output fields to include (optional) DATE OPTIONS (mutually exclusive - only ONE allowed): - usePreviousClose=true: Use previous market close (DEFAULT - use this when user does not specify) - useLiveData=true: Use live intraday market data - pricingDate: Use specific historical date (YYYY-MM-DD) SETTLEMENT NOTE: Setting a custom settlementDate should NOT change the pricing date or globalSettings. Only set settlementType to 'CUSTOM' and provide settlementDate on the bond. FLOATER/FORWARDS NOTE: When user asks to "use forwards" or "run with forwards", apply floaterSettings: { useForwardIndex: true } to ALL bonds in the request, not just FRNs. KEYWORDS NOTE: Prefer omitting keywords entirely for cashflow queries to get all data. If keywords are used, the cashflow section keyword is "dataPaymentList" (NOT sub-field names like paymentDate or principal). NOTE: dataPaymentList is returned in columnar format as { columns: string[], rows: any[][] } for token efficiency, not as an array of objects. ASYNC STATUS CHECK: If a previous calculation was still processing (returned jobRef and requestId), call this same tool with only { "jobRef": "...", "requestId": "..." } to check if results are ready. Do not include bonds or other parameters when checking status.

fixed_income_cashflow_analytics

Retrieve interest rate curves and related data via YieldBook Curves API. Returns par rates, spot rates, forward rates, and discount factors for specified curve types and currencies. USE THIS TOOL when the user wants to retrieve or view a yield curve. CURVE FORMAT: curves: Array of curve request objects, each with: - curveId: Curve identifier (REQUIRED). MUST be unique across all curves in the request. Use a descriptive label like "USD_GVT", "EUR_SWAP_RFR", etc. to distinguish each curve. Do NOT reuse the same curveId for different curves. - curveType: Type of curve (REQUIRED, e.g., "GVT", "SWAP", "SWAP_RFR", "GVT_MUNI") - currency: 3-letter ISO currency code (REQUIRED, e.g., "USD", "EUR", "GBP", "JPY") - expandCurve: Return full curve detail (optional, DEFAULT false) - pricingDate: Historical date for curve data in YYYY-MM-DD format (optional) - showSpotRate: Include spot rates (optional, DEFAULT false) - showForwardRate: Include forward rates (optional, DEFAULT false) - showDiscountFactor: Include discount factors (optional, DEFAULT false) - forwardPeriod: Forward period in months (optional, DEFAULT 0) - impliedForwardDelay: Implied forward delay in months (optional, DEFAULT 0) - index: Index name for the curve (optional) - useLiveCurve: Use live/real-time curve data (optional, DEFAULT false) EXAMPLE - Basic curve retrieval: { "curves": [ { "curveId": "USD_GVT", "curveType": "GVT", "currency": "USD" } ] } EXAMPLE - Full curve with all rate types: { "curves": [ { "curveId": "TEST", "curveType": "SWAP_RFR", "currency": "USD", "showSpotRate": false, "showForwardRate": false, "showDiscountFactor": false, "expandCurve": false } ] } EXAMPLE - Multiple curves (note unique curveIds): { "curves": [ { "curveId": "USD_GVT", "curveType": "GVT", "currency": "USD" }, { "curveId": "USD_SWAP_RFR", "curveType": "SWAP_RFR", "currency": "USD", "index": "SOFR" }, { "curveId": "EUR_GVT", "curveType": "GVT", "currency": "EUR" } ] } DEFAULTS: expandCurve=false, showSpotRate=false, showForwardRate=false, showDiscountFactor=false unless explicitly told to be true. OUTPUT FORMAT NOTE: The "points" array in curve responses is returned in columnar format as { columns: string[], rows: any[][] } for token efficiency, not as an array of objects.

fixed_income_curves

Retrieve historical data for a bond via YieldBook Historical Data API. Returns time-series data for a specified keyword (metric) and date range. REQUIRED PARAMETERS: - identifier: A single TBA bond identifier (CMOs are NOT supported). Accepts: agency coupon identifiers (e.g., FNMA5-GEN, FNMA5.5-GEN, GNMA6-GEN) or CUSIPs starting with 99999 or 01F0 (e.g., 999997LI, 999990CV). Do NOT pass CMO identifiers - those carry a tranche in parentheses (e.g., FNMA11.100(F), GNMA230.100(BA)), use the origination-year.series form (e.g., FNMA11.100), or have a non-TBA CUSIP prefix; they will be rejected. - keyword: The data metric to retrieve (e.g., "yieldToPut" for yield/ YIELD/ yield to put/ yield to price, "price" for price/ PRICE, "oas.LMM" for option-adjusted spread). - startDate: Start date for historical data in YYYY-MM-DD format. OPTIONAL PARAMETERS: - frequency: The sampling frequency for historical data points. Supported values: DAILY, WEEKLY, MONTHLY, QUARTERLY, YEARLY. DEFAULT: DAILY. - endDate: End date for historical data in YYYY-MM-DD format.It is needed for a time-series/range query when user provides a frequency or gives it explicitly. DATE & FREQUENCY HANDLING: - A single startDate with no frequency = point/snapshot query; - Providing a frequency makes this a time-series query. When the user names a period (e.g. "daily for May 2026"), set startDate to the first day of that period (2026-05-01) and endDate to that month's end-of-month / EOM date (2026-05-31). - If the named month is the current month, cap endDate at today. RETURNED INFORMATION: - Historical time-series data for the requested metric // - Data points with dates and values for the specified keyword USE CASES: 1. **Historical price analysis**: Track bond price changes over time KEY FEATURES: - Single identifier per request (identifier goes in the URL path) - Flexible date range selection - Multiple data metrics available via keyword parameter ASYNC STATUS CHECK: If a previous request was still processing (returned jobRef and requestId), call this same tool with only { "jobRef": "...", "requestId": "..." } to check if results are ready. Do not include other parameters when checking status. EXAMPLE - "Give me the yield history for bond 999997LI from May 14, 2026" {"identifier": "999997LI", "keyword": "yieldToPut", "startDate": "2026-05-14"} EXAMPLE - "Give me daily price history for bond 999990CV from May 14, 2026" {"identifier": "999990CV", "keyword": "price", "startDate": "2026-05-14", "frequency": "DAILY"} EXAMPLE - "Give me daily price history for bond 999990CV for May 2026" {"identifier": "999990CV", "keyword": "price", "startDate": "2026-05-01", "endDate": "2026-05-31", "frequency": "DAILY"}

fixed_income_hist_data

**If the user specifies yieldbook or YB or yb, use THIS tool (fixed_income_risk_analytics). Do NOT use a QPS tool.** **If the user says run a PY / do a PY / run py on a bond, use THIS tool.** **If the user asks for projected speeds, forward-looking speeds, or prepayment projections on a bond or MBS without explicitly asking for actual-vs-projected history, use THIS tool.** DO NOT USE THIS TOOL for yield curve retrieval (use fixed_income_curves) or rate shock/scenario analysis on bonds (use fixed_income_scenario_analytics). **BEFORE CALLING: Count bonds first. MAX 50 BONDS PER CALL.** If user has >50 bonds, split into multiple calls BEFORE executing. Do NOT attempt >50 bonds - it will fail. Calculate bond price/yield metrics via YieldBook PY API. Computes pricing, OAS, duration, convexity, DV01, spreads, and accrued interest. SUPPORTS: Government, Corporate, MBS/CMBS, ABS, Municipal, Callable/Putable, FRN, TIPS, Bond Future, Swap. REQUIRED PARAMETERS (per bond): - identifier: Bond ID (CUSIP, ISIN, or YieldBook ID). FNMA or GNMA or similar IDENTIFIER FORMAT: If a user provides space-separated notation like FNMA11.100 F or FNMA20.100 BA, change it to FNMA11.100(F) or FNMA20.100(BA) by replacing the space with parenthesis automatically. If FNMA200.100 or similar id is provided without any letter, pass it as is (no parentheses needed). If ticket has # like N25.1(#1), pass as is. - level: Price/yield input like "100" (price), "100d" (dollars), "4.5y" (yield), "75/i" (spread) - curve: Must include curveType - use "SWAP_RFR" (SOFR, recommended) or "GVT" (government) MBS/TBA/CMO DEFAULTS — ALWAYS INCLUDE THESE for mortgage-backed securities: When pricing MBS, TBA, CMO, or ABS bonds (identifiers like FNMA*, FHLMC*, GNMA*, or CUSIPs for MBS pools), you MUST include ALL of the following in the FIRST call: 1. volatility: {"type": "Default"} — required for OAS/option-adjusted calculations on MBS. Omitting this causes a "Volatility model is not defined" error. 2. extraSettings: {"optionModel": "OASEDUR"} — required for spread-based analytics on mortgage bonds. These two are MANDATORY for MBS. Do NOT omit either of them. Example MBS bond: {"identifier": "FNMA6.5-TBA", "level": "100", "curve": {"curveType": "SWAP_RFR"}, "volatility": {"type": "Default"}, "extraSettings": {"optionModel": "OASEDUR"}} NOTE: Do NOT include prepaySettings unless the user explicitly requests a specific prepay model or rate. OPTIONAL PARAMETERS: - idType, settlementType, settlementDate, userTag - prepaySettings (MBS/ABS): ONLY if user requests a specific prepay model/rate. {type, rate}. Types: Model (25.1), OldModel (24.1), CPR (e.g., 6=6% CPR), PSA (e.g., 150=150% PSA). Omit entirely otherwise — API defaults are sufficient. - volatility: {type, rate}. Use "Default" for standard vol. Other types: LMMSOFR, LMMSkew, Single, Market, etc. The "rate" field is ONLY allowed when type is "Single". Pass the user's number exactly as given — do NOT divide by 100. - globalSettings: pricingDate (YYYY-MM-DD), useLiveData, usePreviousClose (only one date option allowed), retrievePPMProjection (boolean, default false — set to true to retrieve monthly prepayment projections) - keywords: Array of output fields to include - extraSettings.includePartials: Set to true to include partial (stub) period cashflows in analytics when user mentions "Calculate Partials", "with Partials on", "with Partial Durations", "Key Rate Durations", or any mention of "Partial", "Partials". Example: {"extraSettings": {"includePartials": true}}. NOTE: ONLY use partialVega if user explicitly says "Partial Vegas" (different from Partial Durations). - extraSettings.partialVega: Set to true to calculate partial vega outputs if user explicitly requests "Partial Vegas" (NOT Partial Durations). Example: {"extraSettings": {"partialVega": true}} - extraSettings.volatilityDuration: Set to true to calculate volatility duration. Example: {"extraSettings": {"volatilityDuration": true}} DATE OPTIONS (mutually exclusive): - usePreviousClose=true: Use previous market close (default, most stable) - useLiveData=true: Use live intraday market data - pricingDate: Use specific historical date ASYNC STATUS CHECK: If a previous calculation was still processing (returned jobRef and requestId), call this same tool with only { "jobRef": "...", "requestId": "..." } to check if results are ready. Do not include bonds or other parameters when checking status.

fixed_income_risk_analytics

**BEFORE CALLING: Count bonds first. MAX 50 BONDS PER CALL.** If user has >50 bonds, split into multiple calls BEFORE executing (e.g., 75 bonds = 2 calls: 50 + 25). Do NOT attempt >50 bonds - it will fail. USE THIS TOOL when the user provides specific bonds (CUSIP, ISIN, or identifier) and asks for rate scenario analysis, rate shocks, parallel/non-parallel curve shifts, bear/bull steepeners, flatteners, or horizon analysis. Analyze bond performance under rate scenarios via YieldBook Scenario API. Supports parallel shifts, non-parallel curve twists (different shifts at 2s/5s/10s/30s), and credit spread scenarios. Calculates total return, OAS, duration/convexity across scenarios. Max 50 scenarios per call. **IMPORTANT - SCENARIO COUNT**: Only create the EXACT scenarios the user requests. Do NOT add extra scenarios (like base case, inverse, or intermediate) unless the user explicitly asks. If user similar to "100bp shock", create ONE scenario with parallelShift=100. If user similar to "compare -50, 0, +50", create THREE scenarios. Each additional scenario adds computation time and cost. BOND FORMAT: bonds: Array of bond objects, each MUST include: - identifier: CUSIP/ISIN (REQUIRED). FNMA OR GNMA or similar IDENTIFIER FORMAT: If a user provides space-separated notation like FNMA11.100 F or FNMA20.100 BA, change it to FNMA11.100(F) or FNMA20.100(BA) by replacing the space with parenthesis automatically. If FNMA200.100 or similar id is provided without any letter, pass it as is (no parentheses needed). If ticket has # like N25.1(#1), pass as is. - settlementLevel: REQUIRED. Format: '{value}{suffix}' — no suffix = price, 'd' = dollars, 'y' = yield, '/i' = spread, 'o' = OAS. Use 100 (par) when user does not specify a price. Only use a specific value if the user provides one. **Examples: "100" (price), "100d" (dollars), "4.5y" (4.5% yield), "75/i" (75bp spread), "75o" (OAS 75bp). When user says "at an OAS of 75", use "75o". When user says "at a yield of 4.5", use "4.5y". When user says "at a spread of 75", use "75/i".** - horizonPricingMethod: ALWAYS set to "Default" unless the user explicitly requests a specific pricing method (e.g., "OAS Change", "Price Change"). "Default" lets the backend choose the optimal method per security type. - settlementType: defaults to 'MARKET' - volatility: defaults to {type: 'Default'} - curve: defaults to SWAP_RFR/USD SCENARIO FORMAT: scenarios: Array of scenario definitions, each with: - scenarioID: Unique identifier (e.g., "scenario-1") - scenarioTitle: Human-readable name - curveShifts: [{year: 2, value: -150}, {year: 5, value: -120}, ...] for non-parallel - OR parallelShift: 100 (bp) for simple parallel shift - shiftType: 'Par'|'Spot'|'Forward' - timing: 'Immediate'|'Gradual'|'AtHorizon' BOND HORIZON SETTINGS: bonds[].horizonInfo: [{scenarioID: "scenario-1", level: "-77", pricingMethod: "Default"}] - level: horizon price/spread (e.g., "-77" for credit spread) - pricingMethod: horizon pricing method for that scenario EXAMPLE - Simple scenario: { "bonds": [{"identifier": "81743EAA9", "settlementLevel": "100"}, {"identifier": "81743EAC5", "settlementLevel": "100"}], "scenarios": [{"scenarioID": "bear-steepener", "scenarioTitle": "Bear Steepener", "curveShifts": [{"year": 2, "value": 10}, {"year": 10, "value": 50}, {"year": 30, "value": 75}]}], "horizon": {"days": 0}, "globalSettings": {"calcHorizonEffectiveMeasures": true} } EXAMPLE - With OAS-based settlement (user says similar to "at OAS of 75 in a 100bp shock"): { "bonds": [{"identifier": "3136A1US2", "settlementLevel": "75o"}], "scenarios": [{"scenarioID": "scenario-1", "scenarioTitle": "+100bp Shock", "parallelShift": 100}], "horizon": {"days": 0}, "globalSettings": {"calcHorizonEffectiveMeasures": true} } EXAMPLE - With credit spread and explicit price: { "bonds": [{"identifier": "001055AF9", "settlementLevel": "109.2143", "horizonInfo": [{"scenarioID": "scenario-1", "level": "-77", "pricingMethod": "Default"}]}], "scenarios": [{"scenarioID": "scenario-1", "curveShifts": [{"year": 2, "value": -150}, {"year": 5, "value": -120}, {"year": 10, "value": -100}, {"year": 30, "value": -80}]}], "horizon": {"days": 0}, "globalSettings": {"calcHorizonEffectiveMeasures": true} } EXTRA SETTINGS (per bond, optional): - extraSettings.includePartials: Set to true to include partial durations in scenario analytics when user mentions "Calculate Partials", "with Partials on", "with Partial Durations", "Key Rate Durations", or any mention of "Partial", "Partials". Example: {"extraSettings": {"includePartials": true}} GLOBAL SETTINGS: - calcHorizonEffectiveMeasures: boolean (default true) — ALWAYS include this explicitly in globalSettings on every call, even if the user did not mention it. Default to true unless the user explicitly asks for false. Example: {"globalSettings": {"calcHorizonEffectiveMeasures": true}}. Do NOT put this in extraSettings or per-bond settings. - retrievePPMProjection: boolean (default false) — Set to true inside globalSettings to retrieve monthly prepayment projections. DEFAULTS: settlementLevel=100 (par), shiftType='Par', timing='Immediate', interpolationType='Years', pricingMethod='Default', curve='SWAP_RFR/USD', usePreviousClose=true ASYNC STATUS CHECK: If a previous calculation was still processing (returned jobRef and requestId), call this same tool with only { "jobRef": "...", "requestId": "..." } to check if results are ready. Do not include bonds or other parameters when checking status.

fixed_income_scenario_analytics

To retrieve time series pricing Interday summaries data or Intraday summaries data(i.e. bar data). Optimize queries to minimize token usage: limit row count when possible.

historical_pricing_summaries