Skip to main content
Glama
Stari-am

griasa

by Stari-am
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Search meetings

search_meetings
Read-onlyIdempotent

Find recorded meetings by title or text, optionally filtered by participant or project; returns ids, dates, participants and summaries so you can open the full transcript next.

Instructions

Find recorded meetings by title or text, optionally with one participant, newest first. Returns id, title, date, participants and summary — never the transcript. Use the id with get_meeting or get_transcript.

Input Schema

NameRequiredDescriptionDefault
limitNoMost meetings to return. Default 10.
queryNoWords to look for in the title or text.
personNoOnly meetings this person took part in.
projectNoOnly meetings filed under this project id, from list_projects.

Output Schema

NameRequiredDescriptionDefault
meetingsNo
returnedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.22
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Only meetings filed under this project id, from list_projects.",
+  "type": "string"
+}
  2. First observedv1.0.21

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description earns credit for the details annotations cannot express: result ordering (newest first), the exact result shape, and the notable boundary that the transcript is never returned. It doesn't mention rate limits or empty-result behavior, but for a read-only search that is minor.

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

Conciseness5/5

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

Two compact sentences: the first defines the search and ordering, the second defines the return payload and the handoff. No filler, and the most decision-relevant information (what to search, what comes back, what to do next) is front-loaded.

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

Completeness4/5

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

With an output schema available the description needn't enumerate return fields, yet it still names them and flags the transcript exclusion, which is the one surprise an agent could hit. The only gap is silence on the project filter and on result-limit behavior, both of which the schema covers.

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 coverage is 100%, so the schema already documents all four parameters, making 3 the baseline. The description adds a little meaning (query matches title or text, person is a single participant filter) but omits the project filter entirely, so it does not enrich every parameter.

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 ("Find recorded meetings by title or text") plus scope details (one participant, newest first), which is more than a restatement of the name. It implicitly separates itself from upcoming-meeting siblings via "recorded" and explicitly names the follow-up tools get_meeting and get_transcript.

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

Usage Guidelines4/5

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

The closing sentence gives clear next-step routing: "Use the id with get_meeting or get_transcript," which tells the agent this is a discovery tool, not a detail-fetch tool. It stops short of stating when not to use it (e.g., versus list_upcoming_meetings or get_next_meeting_brief), so there is no explicit exclusion.

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

Deploy Server

Other Tools