Clearskies

Discards an agent's pending draft variant, reverting to the published configuration. The agent must be published and have a draft. The draft is deleted.

agents_discard_draft

Discards a workflow's pending draft, reverting to the published configuration. The workflow must be published and have a draft. The draft is deleted.

workflows_discard_draft

Copies an agent as a new draft (the name gets a ' (copy)' suffix). Does not publish. Returns the new agent with status:'draft' and published:false.

agents_duplicate

Copies a workflow as a new draft (the name gets a ' (copy)' suffix). The copy takes the source's latest configuration: its pending draft when one exists, otherwise the published live config. Does not publish — publishing is a separate, explicit step. Returns the new workflow with status:'draft' and published:false.

workflows_duplicate

Returns one agent including its published and/or draft variant. Also returns a draftHistory summary and accepts an optional `version` to return that historical version's full content in requestedVersion.

agents_get

Returns the rules for building an agent in this tenant: command/shortcut constraints, the available model catalog (with allowed verbosity and reasoning effort per model), and supported tools. Call this before creating or publishing an agent.

agent_capabilities_get

Returns one agent folder by id.

agent_folders_get

Retrieve content (call transcript, email body, etc.) for one or more specific events. Use after events are identified (e.g. via events_list or events_search). For meetings, content.meeting.calls is a list — a meeting can have multiple linked recordings (retried recordings, reused calendar links, multiple recording providers); inspect each call and pick the one the user is asking about.

events_get_contents

Return the authenticated user and tenant from the database (userId, personId, name, email, optional photo URL, tenant name). Use to verify which account and user are in scope before other tools. personId is the caller's identity for ownership filters; prefer the ownedByMe argument on list tools over filtering by this id manually.

identity_get

Return all fields for an object type (metadata and validFilters for list tools). Use objectType from object_definitions_list.

object_get_fields_schema

Retrieve calendar events starting within a specified time window. Use for precall prep automation to find meetings that need preparation.

calendar_get_upcoming

Returns one workflow including its live (published) and draft configurations, clearly labeled. Also returns a draftHistory summary and accepts an optional `version` to return that historical version's full configuration in requestedVersion.

workflows_get

Returns a Markdown guide to building workflows for this tenant: node types and their required fields, trigger types and which are runtime-supported, variable syntax, the draft-vs-published model, and worked examples. Call this first before creating or editing a workflow.

workflow_capabilities_get

Returns one workflow folder by id.

workflow_folders_get

Get a single workflow run by id, including full per-step status, inputs, outputs, errors, and timing. Use workflow_runs_list to find run ids, then this to inspect one run in detail.

workflow_runs_get

Get a workflow test run (dry run) by its testRunId, including status and per-step results. testRunId comes from workflow_test_run_start. While the run is still pending or running the response carries retryAfterSeconds — wait that many seconds, then call this again; the field is absent once the run has finished.

workflow_test_run_get

Lists a workflow's referenceable template variables as a compact skeleton: the trigger entity and each findRecords/createSalesforce step, each with its objectType, objectPath (e.g. find-1.records), cardinality, system fields, and inline `references` to related objects. It does NOT enumerate scalar fields — call object_get_fields_schema with a node's objectType to list them, then reference a value as {{<objectPath>.<fieldName>}} (e.g. {{find-1.records.subject}}). Each `reference` lists `subFields` that always resolve (id/name, or person identity fields) plus a `drillable` flag: when true, call object_get_fields_schema(referenceToObj) for additional fields that resolve one hop deep; when false, only `subFields` resolve. createSalesforce records carry no drillable references — their fields (including id/reference fields like OwnerId) are listed by object_get_fields_schema. Provide either an existing workflowId or an inline configuration you're drafting.

workflow_variables_get

Retrieve sales deals or opportunities associated with a specific account. Use for questions about pipeline, revenue, or deal status.

account_get_deals

Retrieve external contacts associated with a specific account. Use after an account has been identified or when the user asks who works at or is linked to an account.

account_get_contacts

Retrieve a list of customer accounts stored in clearskies. Use when the user asks about existing accounts, customers, or organizations. Search matches both account names and domain names. If searching for 'goodwaygroup.com', it will match accounts with that domain. Try partial company names if full name doesn't match. For 'my accounts' or 'accounts I own', set ownedByMe: true to scope to the current user's owned accounts (resolved server-side; do not look up an owner id). If ownedByMe returns an error, relay that message to the user and do not retry the request without ownedByMe.

accounts_list

Lists an agent's draft edit history, newest first: each entry has the version number, change kind, who edited it, when, and a delta of what changed from the previous version — but NOT the full content. To fetch a version's full content, call agents_get with that version number. Requires agentId; paginated with itemsPerPage and an opaque cursor.

agent_draft_history_list

Lists agent folders. Omit arguments to list all folders, set rootOnly:true for root folders, or pass parentId to list direct child folders.

agent_folders_list

Lists agents (id, name, status). Filter by status.

agents_list

List synced records for a custom CRM object type (rows in crm_records). Use object_definitions_list for objectType values. For standard objects (account, contact, deal, employee), use accounts_list, contacts_list, deals_list, or employees_list instead. Supports search on the name field, field filters (see object_get_fields_schema), pagination, and optional id filter. Pass linkedAccountIds (clearskies account IDs from accounts_list) to return only records linked to those accounts — e.g. Salesforce notes attached to a given account.

crm_records_list

List Slack and Microsoft Teams channels synced into clearskies, each with the account(s) it is linked to. Use this to answer a question about a chat channel referred to by name (e.g. "what's been discussed in the deal-room channel?" or "summarize the GenePoint Teams channel"): call channels_list with the channel name in `search`, take the matching channel's linkedAccounts[].id, then pass that account id to events_list (or events_search) to read the messages. This is the only path from a Teams channel to its content — Teams channels are not returned by events_search. Filter by `source` ('slack' or 'ms_teams') or set `linkedOnly` to only channels tied to an account. If several channels share a name (every Teams team has a 'General'), disambiguate by teamName or linked account.

channels_list

Retrieve the people involved in a specific deal — its stakeholders — each with every source's claim about their part in it. Use when the user asks who is on a deal, who the champion, decision maker or economic buyer is, who to contact about it, or which of our own team is working it; also use it to check whether a deal has an identified buying committee at all. Returns one row per person — external contacts and internal employees alike, see `personType` — with a nested `links` array holding one entry per source that connected them to the deal. Read `links` before asserting a role: a `salesforce` or `hubspot` link is a recorded CRM fact (confidence 1.0, and on Salesforce `isPrimary` marks the primary contact role), while an `llm` link is inferred from call, email and Slack content and its `confidence` (0-1) is the model's own score. The same person often carries several links and the sources can disagree; when they do, attribute each role to its source rather than merging them. Roles are free text from each source, not a fixed vocabulary. People are ranked CRM-confirmed first, then by confidence. An empty result means no source has linked anyone to this deal — it is not evidence that the deal has no stakeholders.

deal_get_people

Retrieve a list of deals stored in clearskies. For 'my deals', 'my opps', or 'my pipeline', set ownedByMe: true to scope to the current user's owned deals (resolved server-side; do not look up an owner id). If ownedByMe returns an error, relay that message to the user and do not retry the request without ownedByMe.

deals_list

List internal company people (employees, teammates). Not customers, prospects, or partners.

employees_list

Retrieve a list of events stored in clearskies. Use when the user asks about meetings, emails, Slack threads, support tickets, or any historical activity. Set the optional query arg for semantic search over event contents (e.g. "calls where pricing was discussed") — it is ANDed with all other filters, so you can combine semantic search with exact filtering (externalIds, provider, time bounds) in one call rather than choosing between this and events_search. Prefer startTime/endTime shortcut args (RFC3339 UTC): startTime is inclusive and endTime is exclusive. These shortcut args map to internal.start_at filters and override any internal.start_at filters passed via filters. When the user asks for "recent", "most recent", or "latest" (past) events, set endTime to now so future scheduled events are excluded. Do not call without date filters when the user has specified a time range or asked for past/recent events. If no events are found for a date range, try widening the range. To find recorded calls across all providers set hasCall true, and set transcriptStatus 'completed' to require a usable transcript; both exclude calendar-only meetings and AND with the optional provider filter. To list the activity linked to a specific deal, filter on internal.deals with a deal id from deals_list — deal links are LLM-inferred, and each returned event lists its linked deals in entities with a confidence score (0-1).

events_list

List external people (customers, prospects, partners). Not internal employees or teammates. Use this to find people across all accounts when you don't know which account they belong to. Searches by name and email. For 'my contacts', set ownedByMe: true to scope to the current user's owned contacts (resolved server-side; do not look up an owner id). If ownedByMe returns an error, relay that message to the user and do not retry the request without ownedByMe.

contacts_list

List GitHub activity (PRs authored/merged/closed, reviews, commits) synced from GitHub, stalest-first. Filter by assignee email (resolved to the person's linked GitHub logins) or an explicit githubLogin, kind, open-only, and updatedBefore (RFC3339) to find PRs that need attention (e.g. open with no recent activity). Returns PR state, draft status, labels, ticket codes, and the upstream last-updated time.

github_activities_list

List configured CRM object definitions for this tenant. Each item's objectType is the value to pass to object_get_fields_schema, crm_records_list, and list-tool filters. Also returns schemaStatus, a compact schema-freshness summary: schemaStatus.fingerprint is a content hash of the query-relevant schema (field ids, labels, types, filters, enum values, references, editability) for every listed object — compare it against a stored fingerprint to decide whether a cached local schema snapshot is still current. schemaStatus.lastCheckedAt is when clearskies last successfully refreshed CRM schema metadata (NOT when the schema content last changed, and NOT a CRM record-sync watermark); this is distinct from when a client generated its local snapshot. Schema-content freshness is signalled by the fingerprint alone, not by any timestamp.

object_definitions_list

List support tickets synced from Linear or Pylon, stalest-first. Filter by assignee email, provider, open-only, and updatedBefore (RFC3339) to find tickets that need attention (e.g. unowned, stale, or not updated in N days). Returns ticket state, lifecycle type, owner, and the upstream last-updated time.

support_tickets_list

Lists a workflow's draft edit history, newest first: each entry has the version number, change kind, who edited it, when, and a delta of what changed from the previous version — but NOT the full configuration. To fetch a version's full configuration, call workflows_get with that version number. Requires workflowId; paginated with itemsPerPage and an opaque cursor.

workflow_draft_history_list

Lists workflow folders. Omit arguments to list all folders, set rootOnly:true for root folders, or pass parentId to list direct child folders.

workflow_folders_list

List execution history for a workflow, including per-step status, errors, and outputs. Use to investigate why a workflow run failed, find runs for a particular account or meeting, or list recent runs by time range. Requires workflowId — get it from a workflow listing surface or workflow URL. Results are ordered most-recent first.

workflow_runs_list

Lists the candidate inputs valid for a workflow's trigger, to use as a test-run input: meetings for meeting triggers (meetingStarted/meetingEnded), Salesforce records for record triggers (salesforceRecordCreated). Pick one and pass its id to workflow_test_run_start (a meetingId for meeting triggers, a recordId for record triggers). Scheduled workflows take no input. Supports search on the candidate label and pagination.

workflow_trigger_records_list

Lists workflows (id, name, status, hasDraft, version). Filter by status. Set includeConfig:true to include each workflow's current configuration — the pending draft when hasDraft is true, otherwise the live one; use workflows_get to see the live and draft configs side by side.

workflows_list

Moves an agent into a folder or to root without changing its draft or published configuration. Pass folderId, or clearFolder:true to remove it from its folder.

agents_move

Moves a workflow into a folder or to root without changing its graph, draft, or publication state. Pass folderId, or clearFolder:true to remove it from its folder.

workflows_move