get_transcript

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

No annotations are provided, so the description carries the full burden. It discloses that transcript content is untrusted user-generated data, returned delimited, and warns against following instructions inside. It also describes the raw_vtt behavior and the ambiguous_match error. However, it does not explicitly state whether the operation is read-only (implicit via 'fetch') or mention any authentication requirements beyond 'invited to', which is a minor gap given the lack of annotations.

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?

Though the description is multi-sentence, every sentence serves a purpose: it defines the action, provides parameter guidance, warns about ambiguity, and flags security considerations. The 'Args' section is clearly structured. No filler or redundant information exists, so the length is justified.

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?

For a tool with two parameters and no output schema, the description is quite complete. It explains the input types, error behavior, and content trust boundaries. However, it does not precisely describe the structure of the default 'speaker-attributed text' return (e.g., segments, timestamps, speaker labels), which an agent might need for downstream parsing. Since no output schema exists, the description could be slightly more explicit about the return format, hence a 4 rather than 5.

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%, but the description fully compensates. For 'meeting', it explains three accepted forms (id, list position, fragment) and the error case. For 'raw_vtt', it describes what it returns instead of speaker-attributed text. This provides meaning well beyond the schema's bare type declarations, which only say 'string' and 'boolean'.

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 states a specific verb and resource: 'Fetch the transcript of a Teams meeting you were invited to.' It clearly distinguishes from sibling tools (auth_status, sign_in, list_recent_meetings, sign_out) by naming the exact object it retrieves. No other tool fetches transcripts, so purpose is unambiguous.

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?

The description provides explicit when-to-use context: it requires an invitation to the meeting. It gives detailed guidance on the meeting parameter, warns about ambiguous_match errors for fragments, and advises checking transcript_status first. It also instructs not to follow instructions in transcript content, which is a usage caveat. This exceeds basic guidance and even names alternatives (list_recent_meetings) for obtaining the correct id.

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