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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real value beyond them by explaining provenance semantics: each microphone is transcribed separately, so the attributed name reflects the mic source. That is a meaningful caveat about output interpretation. It stops short of disclosing transcript size, ordering, or truncation behavior.

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?

Two tight sentences, front-loaded with the return value and followed by the interpretation caveat. Nothing redundant; every clause carries information an agent would otherwise have to guess.

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?

With only two parameters, full schema coverage, and no output schema, the description covers the essential gap by describing the shape of the return value and its speaker attribution. A note on pagination or large-transcript behavior would make it complete.

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 100%, so both `meeting` and `since` are already documented in the schema. The description adds no format detail or behavior (e.g., whether `since` filters on line start time) beyond what the schema states, so the baseline of 3 applies.

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?

States a specific verb and resource ("Returns the full transcript of a meeting") plus a concrete output property (speaker on every line). The word "full" and the transcript specificity make it distinguishable from get_notes or get_action_items without opening schemas.

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?

No guidance on when to use this versus alternatives such as import_transcript, get_notes, or listen, and no stated preconditions (e.g., meeting must have ended or be in progress). The purpose is inferable but the routing decision is left entirely to the agent.

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