Tool4seller
Amazon seller analytics
- Category
- Commerce
- Primary Subcategory
- Marketplace Seller, Dropship & Wholesale Tools
Integration details
Description
Tool4seller helps Amazon sellers inspect their authorized store, sales, profit, inventory, review, inbound shipment, advertising, and sales traffic data directly in ChatGPT. The app provides read-only business analytics so users can ask operational questions, compare performance, and review marketplace status without changing account data.
- Integration type
- Plugin
- Verification status
- Not applicable
- Platform
- ChatGPT
- Primary Subcategory
- Marketplace Seller, Dropship & Wholesale Tools
- Secondary Subcategories
- None listed
- Brand
- Tool4seller
- Access
- Account required
- First tracked
- 2026-07-04
- Tool count
- 32
- Geography
- US
The Primary Subcategory used for this profile’s headline score.
Other Subcategories where the Integration is listed.
Get alerts for Tool4seller
Get updates when Tool4seller’s Discoverability Score or category rank changes.
ChatGPT Plugin Discovery Score
ChatGPT Plugin discovery is coming soon
ChatGPT can surface a Plugin when it matches a user's request.Your Plugin Discovery Score measures how often yours appears.
No spam. Unsubscribe any time.
What discovery looks like

Competing in ChatGPT Marketplace Seller, Dropship & Wholesale Tools
View Category32 tools agents can invoke
Applies only a previously confirmed immutable plan to the authorized Amazon Ads account, including creating ads, overwriting settings, or irreversibly archiving negative targeting entities; Review Sandbox simulates these writes. Requires its one-time confirmation receipt and an idempotency key. Generate a new idempotency key for every newly prepared plan; reuse the exact key only to retry apply for the same plan. If this call times out or disconnects, do not prepare a replacement: query get_workflow_plan, or retry this exact plan with the same idempotency key. An INDETERMINATE item means Amazon may have accepted the write and must be reconciled before any retry. For an AD_STRUCTURE_CREATE plan, pass applyContinuation returned by continue_workflow_draft. After the approved write finishes, the server automatically prepares and returns the next stage preview; do not ask the customer for permission merely to advance stages. In particular, after an automatic-target bid plan succeeds, present any returned MANUAL positive-targeting batch preview or selection action in the same customer response; never stop at the four successful automatic bids while manual groups remain. Standalone Campaign, Ad Group, and Product Ad create results return ordered nextActions. Present or execute the immediate read/plan-preparation action when its inputs are already known; do not reduce it to a generic offer to continue.
apply_workflow_plan
Cancels a prepared or confirmed plan before business changes are applied.
cancel_workflow_plan
Confirms the exact immutable plan the customer reviewed. Call only after explicit customer approval of old/new values.
confirm_workflow_plan
Diagnoses advertising efficiency with read-only advertising metrics for one store and business date range. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
diagnose_ad_efficiency
Diagnoses profit anomalies with read-only profit, sales, and advertising signals for one store and business date range. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
diagnose_profit_anomaly
Diagnoses sales changes with read-only sales, traffic, advertising, and inventory signals for one store and business date range. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
diagnose_sales_change
Discovers Tool4seller MCP workflow capabilities, related tools, required inputs, execution availability, and suggested next actions for business diagnosis or structured draft collection. Returns MCP reporting date limits and range-splitting guidance.
discover_capabilities
Returns the current user's default currency, time zone, display language, and creation time.
get_current_user
Returns the current owned workflow draft without modifying it, including its effective expiry state, optimistic-lock version, missing inputs, validation errors, recommended next actions, and persisted continuation state.
get_workflow_draft
Gets a workflow plan without modifying it, returning its effective expiry state, persisted execution status, item errors, upstream diagnostics, and explicit old/new values. After a timeout or disconnected apply call, query this exact plan (or retry apply with the same idempotency key); never create a replacement plan until its outcome is terminal and any INDETERMINATE items have been reconciled.
get_workflow_plan
Reviews inventory risk with read-only inventory and inventory alert signals for one store. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
inventory_risk_review
Returns paginated FBA inbound shipment items for up to 100 shipment IDs.
list_inbound_shipment_items
Returns paginated FBA inbound shipments for authorized sellers.
list_inbound_shipments
Returns sellers, marketplaces, SP API status, Advertising API status, and active status for the current user.
list_stores
Creates or incrementally updates an AD_STRUCTURE_CREATE draft. Collect the Sponsored Products Campaign/Ad Group/Product Ad structure and any targeting the customer already supplied. One MANUAL ad group can contain only one positive targeting family: KEYWORD or ASIN TARGET. If positive targeting is omitted, collect manualTargetingFamily=KEYWORD|TARGET before execution. If the customer wants both, model separate manual Campaign/Ad Group structures from the start and assign one family to each; never put both into one ad group. Every ad group needs a negative-targeting decision: supplied allowed negative items automatically record negativeTargetingMode=CONFIGURED; when none are supplied, recommend negatives and ask the customer to choose CONFIGURED or NONE. AUTO permits both negative keywords and negative ASINs; a MANUAL KEYWORD group permits only negative keywords, and a MANUAL TARGET group permits only negative ASINs. Continuation prepares all Campaigns together, then all Ad Groups, then all Product Ads across every ad group in one multi-group plan before any AUTO bid decision or MANUAL recommendation can pause the draft. After all Product Ads exist, continuation queries and persists Amazon recommendations only for each manual ad group's recorded family, asks the customer to choose up to 100 candidates, obtains suggested or custom bids, then combines all ready MANUAL positive targeting into one Targeting batch plan. It subsequently combines every configured negative targeting item across AUTO and MANUAL structures into one separate negative Targeting batch plan. AUTO-only drafts skip the MANUAL stage and MANUAL-only drafts skip the AUTO stage. If recommendations are absent or rejected, submit customer-approved customCandidates of the same family to the continuation; do not recreate the already-created structure. For every AUTO ad group, explain that Amazon creates exactly four targets after the ad group exists and record automaticTargetBidding.mode as KEEP_DEFAULT, AMAZON_SUGGESTED, CUSTOM, or DECIDE_LATER; CUSTOM requires all four official theme bids. Never model those themes as manually created targets. Every supplied nested entity requires a stable clientRef. Updating requires draftId and expectedDraftVersion; arrays merge by clientRef and remove only through removeClientRefs. When the draft is READY, call continue_workflow_draft. The server then persists the current atomic plan, created Amazon IDs, recommendation choices, and bid choice so later calls safely resume. Every returned write plan must still be shown, explicitly confirmed, and applied. Pass applyContinuation to apply_workflow_plan so successful writes automatically prepare the next stage; never ask the customer for permission merely to advance. Recommendation 429 responses are recoverable and do not create a write plan. During draft collection, accept syntactically valid SKU/ASIN values without querying Inventory or Listings; production Product Ad plan preparation performs product resolution.
prepare_workflow_draft
Creates and persists an immutable workflow plan with explicit old and new values. Do not manually compose atomic AD_CAMPAIGN_CREATE, AD_AD_GROUP_CREATE, AD_AD_CREATE, or AD_TARGETING_CREATE plans for a dependent advertising structure. Start with an AD_STRUCTURE_CREATE draft and use continue_workflow_draft so the server persists dependencies and prepares the next atomic plan. Atomic creation plans remain available for standalone resource requests. Use AD_CAMPAIGN_CHANGE for campaign daily-budget, ENABLED/PAUSED state, or name changes selected by IDs or campaign metric rules. Use AD_CAMPAIGN_CREATE to create customer-reviewed ENABLED campaigns. Each campaign requires adProduct=SPONSORED_PRODUCTS, name, targetingType=MANUAL|AUTO, and dailyBudget. Optional bidStrategy accepts FIXED, DYNAMIC_DOWN_ONLY, or DYNAMIC_UP_AND_DOWN and defaults to DYNAMIC_DOWN_ONLY. Optional placementBidAdjustments accepts TOP_OF_SEARCH, PRODUCT_PAGE, REST_OF_SEARCH, or SITE_AMAZON_BUSINESS with a unique placement and percentage from 0 through 900. Dates and portfolio are optional. dailyBudget currency is derived from the selected store marketplace; do not supply a currency field. Campaign plans expose reachScope.mode=AMAZON_ONLY, meaning ads are limited to Amazon owned-and-operated properties. Present this setting in the customer's language using the reachScope display name and description. Do not expose the underlying Amazon API value MINIMIZE_SPEND unless explicitly requested. Use AD_AD_GROUP_CHANGE for ad-group default-bid, ENABLED/PAUSED state, or name changes. Use AD_AD_GROUP_CREATE to create customer-reviewed ENABLED Sponsored Products, Sponsored Display, or Sponsored Brands ad groups; resolve adProduct from the parent campaign. defaultBid is optional for SP/SD, while SB does not support it and supplied values are ignored. For SP AUTO, pass the recorded automaticTargetBidding choice: KEEP_DEFAULT, AMAZON_SUGGESTED, CUSTOM with exactly four theme bids, or DECIDE_LATER. Amazon creates the four theme targets after the ad group exists and the server synchronizes them; do not use AD_TARGETING_CREATE for them. After creation, follow automaticTargetBidNextAction. Suggested mode calls query_advertising_bid_recommendations for all four IDs; custom mode provides the AD_TARGETING_CHANGE plan arguments. Always show final bids and obtain separate confirmation before applying target changes. Use AD_AD_CREATE to create ENABLED product ads under Sponsored Products or Sponsored Display ad groups; use adGroupId plus skus/asins for one group, or adGroups[] for one immutable multi-group plan. SP uses PRODUCT_AD/productCreative and SD uses COMPONENT/responsive eCommerce componentCreative. Non-empty skus takes precedence over asins within each group and live products must exist in Listings with both SKU and ASIN. Use AD_AD_CHANGE for ad ENABLED/PAUSED state changes or Sponsored Brands ad name changes. Use AD_TARGETING_CHANGE for positive keyword/Target bid or state actions and for ENABLED/ARCHIVED negative keyword/negative ASIN Target actions. Use AD_TARGETING_CREATE to create ENABLED positive keywords, positive exact-ASIN Targets, negative PHRASE/EXACT keywords, or negative exact-ASIN Targets after customer review. Use the legacy top-level targetType shape for one group, or targetingGroups[] to combine multiple target types/ad groups into one immutable plan; execution remains grouped by targetType, campaignId, and adGroupId with item-level results. Resolve the advertising product from the selected campaign or ad group before requesting targeting details. Sponsored Display supports no keywords or negative keywords: for an SD product exclusion use NEGATIVE_TARGET with adGroupId and targets[].asin only, without keywordText or PHRASE/EXACT matchType. For Sponsored Brands negative creation, match the negative targeting family to the ad group's synchronized positive targeting entities: keywords require NEGATIVE_KEYWORD and Targets require NEGATIVE_TARGET. Pass selector + action operations resolved from this or prior turns. A positive Target and its campaign/ad group may be enabled or paused when changing its bid; do not require a paused Target to be enabled first. Archived entities are not writable. Negative targeting entities support SET_STATE only: PAUSED can become ENABLED or ARCHIVED, ENABLED can only become ARCHIVED, and ARCHIVED is terminal. They do not have bid or performance-metric actions. Every action object uses exactly type and value; for negative SET_STATE put ENABLED or ARCHIVED in action.value, never action.state. Prefer stable keywordIds or targetIds returned by queries and descriptive operationIds instead of RULE_1-style ordinals; operation selectors must not overlap. Each item returns the matched selector and action snapshot. This tool never applies changes.
prepare_workflow_plan
Returns store-level advertising performance or paginated advertising performance metrics grouped by SKU, ASIN, or parent ASIN for a single store and business date range. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_advertising
Returns current advertising ad groups with stable IDs, name, state, serving status, default bid, parent campaign including campaignType, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. Results can proceed to AD_AD_GROUP_CHANGE, AD_AD_CREATE, or AD_TARGETING_CREATE. AD_AD_CREATE resolves the product-specific creative: SP uses PRODUCT_AD/productCreative and SD uses COMPONENT/responsive eCommerce componentCreative. Choose targeting inputs from campaign.campaignType: Sponsored Display supports ASIN Targets and negative ASIN Targets only, never keywords or negative keywords.
query_advertising_ad_groups
Returns current Sponsored Products, Sponsored Display, and Sponsored Brands ads with stable ad IDs, product identity or name, state, serving status, parent references, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. Results can proceed to AD_AD_CHANGE for confirmed ENABLED/PAUSED state changes or Sponsored Brands name changes.
query_advertising_ads
Returns advertising campaign performance or daily campaign performance. Summary reports support standardized campaign attribute and aggregated metric filters. When the user specifies any supported attribute or metric condition, pass it through filters in the first call; do not retrieve unfiltered pages and filter locally. Paginate only the filtered result. Always retain and present each campaign's current budget from budget.currencyAmount with budget.currencyCode. For budget changes, show current budget -> planned budget before requesting confirmation. Results can proceed to AD_CAMPAIGN_CHANGE for customer-confirmed daily-budget, ENABLED/PAUSED state, or name changes, and Sponsored Products, Sponsored Display, or Sponsored Brands campaigns can proceed to AD_AD_GROUP_CREATE. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_advertising_campaigns
Returns paginated negative keyword or negative ASIN management records with stable IDs, state, serving status, match details, parent campaign/ad group references, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. Historical ENABLED, PAUSED, and ARCHIVED states remain queryable. Results can proceed to AD_TARGETING_CHANGE to re-enable legacy PAUSED entities or archive PAUSED/ENABLED entities; PAUSED is not a writable target state, ARCHIVED is terminal, and negative targeting entities do not support bid actions or performance metrics.
query_advertising_negative_targets
Returns current Amazon Ads portfolios with stable portfolio IDs, names, states, serving status, budget policy and amount, budget dates, in-budget status, and Amazon createdAt/updatedAt timestamps as UTC ISO-8601 instants. This management query does not return performance metrics.
query_advertising_portfolios
Returns purchased product performance attributed to advertised products. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_advertising_purchased_products
Returns product-scoped buyer search term performance or product-ASIN search term performance. When a manual AD_STRUCTURE_CREATE draft has productAds but lacks positive targeting, use dimension=sku|asin|parentAsin with values to find evidence-backed keyword or product-target candidates. Sort by adOrders, adSales, or roas to surface historical performers. The returned average CPC can be presented as a historical bid reference, but it is not an Amazon suggested bid. Show the supporting metrics and obtain customer approval before adding any candidate or bid to the draft. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_advertising_search_terms
Queries advertising keyword, explicit ASIN, product-category, automatic theme, or keyword-group theme target performance, including current targets with zero traffic in the date range. Product-scoped historical keyword or explicit-ASIN results can provide evidence for targeting candidates when a manual AD_STRUCTURE_CREATE draft lacks positive targeting. Average CPC is a historical bid reference, not an Amazon suggested bid; show supporting metrics and obtain customer approval before reusing a target or bid. dimension/values provide product scope; filters enables store-level target attribute and aggregated metric search and cannot be combined with product scope. When the user specifies a supported attribute or metric condition, pass it through filters in the first call; do not retrieve unfiltered pages and filter locally. Paginate only the filtered result. Query results can proceed to AD_TARGETING_CHANGE for bid or ENABLED/PAUSED state changes. Enabled and paused positive Targets can change bids without enabling them first; archived entities are not writable. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_advertising_targets
Returns paginated inventory listing data for a single store. FBA-specific fields are populated only for AFN inventory and are null for MFN inventory when not applicable.
query_inventory
Returns low stock, excess stock, long-term storage, or recommended removal inventory alerts.
query_inventory_alerts
Returns store-level profit summaries or paginated profit data by SKU, ASIN, or parent ASIN for a single store and business date range. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_profit
Returns paginated rating data for parent ASINs that have review tracking enabled in a single store. Parent ASINs without review tracking or rating data are omitted from the response.
query_review_ratings
Returns sales summaries, daily sales summaries, SKU sales, or daily SKU sales for a business date range. The range is inclusive and each request may contain at most 95 calendar days. When splitting a longer range, set endDate to startDate plus 94 days, then start the next range at the previous endDate plus 1 day; a 95-day difference between startDate and endDate would contain 96 inclusive days and is invalid. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_sales
Returns sales traffic summaries or paginated sales traffic metrics by ASIN or parent ASIN for a single store and business date range. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_sales_traffic
Runs a read-only store health check by combining sales, profit, advertising, and inventory signals for one store and business date range. MCP reporting and workflow metric date ranges use yyyy-MM-dd and include both startDate and endDate, with at most 95 calendar days per range. For longer read-only reports, split into non-overlapping windows: endDate = startDate plus 94 days, capped at the requested end date; the next startDate is the previous endDate plus 1 day. Apply the same limit independently to comparison ranges. Do not average ratios such as ACOS or ROAS across windows; recompute them from summed base metrics. Do not automatically split advertising write plans or metric-based selectors; obtain a supported analysis window from the user. This reporting limit does not apply to campaign scheduling dates.
query_store_health
How do I improve a ChatGPT Plugin's discoverability?
The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.
What are Tool4seller alternatives on ChatGPT?
As of 2026-09-28, Tool4seller competes with Adzviser Amazon Seller Central, Catalog CLI Pro, DataGlass, Dropshipping Product Scout, El Tasador - Soluna, Faire Wholesale, First FMCG, Flippo AI, Floaro, Helium 10, ListingForgeAI, Nifty, NovaSupplier, Pattern Intelligence, Product Listing Validator, sedoriMAX, Sellerise, Syncee AI Dropship & Wholesale, Zendrop in ChatGPT Marketplace Seller, Dropship & Wholesale Tools, ranked by public Discoverability Score.
Where is this profile measured?
This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.