Sliq

Search meetings

search_meetings

Read-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)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "where_clause": "<where_clause>"
    },
    "name": "search_meetings"
  }
}

Input 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
`on_behalf_of`	No	A teammate's email, or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account.
`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%'

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 6, 2026

changedInput schema / properties / on_behalf_of / description

Previous value: -"An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."New value: +"A teammate's email, or an agency client's from list_agency_clients, to run this call in that account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."

Changed1 schema field changedOct 19, 2026

addedInput schema / properties / on_behalf_of

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}

First observedSep 15, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so safety is covered; the description adds real value by disclosing the return shape (count, truncated, meetings), the truncation thresholds (summary 6000, transcript 10000), and how to recover full transcripts. The only wrinkle is the slightly confusing statement that Fathom data is "local and faster" inside a sentence telling the agent to prefer this tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Short and front-loaded, with the search statement and routing rule ahead of return-value detail; the summary/returns wrapper tags make it scannable. Minor redundancy in repeating the where_clause column list that already lives in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates fully by describing the returned dict, truncation behavior, and the follow-up tool for full transcripts. Combined with complete parameter docs, an agent has everything needed to call and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and every parameter already documents its default and meaning, including the JSONB `::text ILIKE` pattern and the offset+=limit paging recipe. The description's restatement of the allowed column list duplicates the schema rather than adding new semantics, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Search user's meeting data from table_meeting_data") and names the sibling families (grain_*/granola_*/otter_*) it overlaps with, so an agent can distinguish it without opening schemas. The reference to get_meeting_transcript for full transcripts further delineates scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing rule: prefer this tool first when Grain/Granola/Otter are connected, and fall back to the provider-specific tools only if there are no relevant results or the user names that source. That is a genuine when-to-use plus alternative-selection condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Sliq tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?