Transcribe Meeting

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

With no annotations at all, the description carries the full behavioral burden and falls short: it does not say whether existing transcripts are overwritten, what happens to the audio file (keep_audio defaults to true but is never mentioned), how long transcription takes, or whether a model must be downloaded. It does disclose the output shape and speaker-labeling scheme, which is the one real behavioral contribution.

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

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

Front-loaded purpose sentence followed by a compact per-parameter list; nearly every line earns its place. The backticked parameter formatting makes it scannable, with only minor redundancy between the language names and their codes.

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

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

An output schema exists, so return values need not be explained, and three parameters are covered, but an agent still lacks the keep_audio semantics and any prerequisite about a recording being available for the session. For a moderately complex, potentially long-running transcription tool with zero annotations, that leaves meaningful gaps.

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

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

Schema description coverage is 0%, so the description must compensate, and it does for three of four parameters (session_id, language, model), including allowed values and the empty-string convention. However, keep_audio — a boolean defaulting to true that likely controls audio retention or deletion — gets no explanation anywhere, leaving a consequential parameter undocumented.

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

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

The description gives a specific verb and resource ('Transcribe meeting audio') plus a concrete output artifact ('synchronized conversation log (Attendees vs Microphone)'), which distinguishes it in spirit from clean_transcript or summarize_meeting. It does not name any sibling, so the differentiation is implicit rather than stated.

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

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

There is no guidance on when to call this versus summarize_meeting, clean_transcript, or start/stop_meeting_recording, and no stated prerequisites such as a completed recording existing for the session. The closest thing to guidance is the 'empty = latest session' note, which is a parameter behavior rather than a usage rule.

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