Search Meetings
search_meetingsRead-only
When the user has Grain, Granola, or Otter connected, prefer this tool first (Fathom data is local and faster) and fall back to grain_*/granola_*/otter_* only if no relevant results or the user explicitly references that source.
Dict with count, truncated, and meetings array (summary truncated to 6000 chars, transcript truncated to 10000 chars — use get_meeting_transcript(id) to fetch the full transcript for a specific meeting)
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results (default 10, max 20). Only override if user says a specific number like "show me 5 meetings". For vague quantities ("couple", "few", "recent"), omit this parameter to use default. | |
| offset | No | Rows to skip for paging (default 0). When the result is truncated, re-call with offset += limit to fetch the next page. | |
| order_by | No | SQL ORDER BY clause (default: meeting_date DESC) | meeting_date DESC |
| where_clause | Yes | SQL WHERE clause (without WHERE keyword). Use ONLY these columns: provider, title, meeting_date, duration, speakers, attendees, meeting_url, share_url, summary, transcript. For speakers/attendees JSONB, use: speakers::text ILIKE '%pattern%' or attendees::text ILIKE '%pattern%' |