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

Annotations declare non-read-only, non-destructive, non-idempotent, open-world. The description adds meaningful context beyond that: the transcript is persisted as a document in the workspace (a side effect worth knowing for a non-read-only tool) and the 25 MB / link-form input constraint. It stops short of explaining failure modes or format of the returned transcript, but the safety profile is already covered by 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?

Three tight sentences: trigger, return/persistence behavior, and routing to the sibling. The trigger condition is front-loaded and every sentence earns its place.

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. For a 3-param, no-enum tool the description covers when to call it, its input boundary, its persistence side effect, and the adjacent tool, leaving no selection gap.

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 url, title and language are already fully documented in the schema. The description only restates the url constraint (https, up to 25 MB) and adds nothing about title or language, so the baseline 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?

Specific verb+resource: transcribes an audio/video recording and returns the transcript while saving it as a workspace document. It explicitly distinguishes itself from the related meeting_notes sibling, so an agent can route without opening either schema.

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?

States the trigger condition clearly (user wants words from a recording and supplies an https link up to 25 MB), then names the alternative (meeting_notes) and the condition that selects it (need notes and action items). Nothing is left to inference.

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