Transcribe a link

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

Annotations only establish that this is a non-idempotent, non-destructive, open-world write. The description adds the behavior an agent actually needs: it is asynchronous, kicks off immediately, consumes account minutes, returns an id rather than the finished text, and never downloads the media. That is substantive context beyond the structured fields.

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, front-loaded with the action, then the accepted sources, then the workflow. Every clause carries information an agent needs; nothing is redundant with the title.

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?

There is no output schema, so the description carries the burden of explaining the return value, and it does: a transcription object with an id plus the polling path to reach the text. Combined with the cost note and source list, an agent has everything needed to invoke and follow up correctly.

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 coverage is 100%, so all four parameters are already documented with meaningful detail (including the captions/minutes tradeoff and the language code format). The description adds no parameter-level information beyond the notion that the input is a link, 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 ("Create a transcription from a link to a video or recording") and enumerates accepted sources. It also explicitly positions itself against the sibling read tools by naming get_transcription and get_transcript as the follow-up steps, so an agent can distinguish it without opening the 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?

Gives a concrete workflow: call this, poll get_transcription until status is done, then read get_transcript. It also flags the cost model ("uses the account's minutes") and that it starts immediately. It stops short of stating when not to use it (e.g. for already-uploaded files or existing transcriptions), so it is strong but not exhaustive.

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