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

Annotations cover the safety profile (readOnly, openWorld, non-destructive), and the description adds real operational context on top: a $0.02/call price with failed calls free, the x402 USDC or card-key auth paths, the 5 MB ceiling, accepted formats, and the practical warning that repeats are not free (which explains idempotentHint=false).

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-loads purpose, then return values, formats, use cases, example, and pricing in one tight block with no filler sentences. Slight redundancy in restating the read-only nature and non-free repeats that annotations already imply, but it is short enough that this does not hurt.

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, and the description compensates by enumerating the return fields (transcript text, detected language, duration, word count) alongside input constraints, pricing, and auth. An agent has everything needed to decide and call 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% and the single url parameter is already documented with the 5 MB cap, so the baseline is 3. The description adds accepted audio formats and a concrete example URL, giving the agent more to go on than the schema alone.

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?

Names a specific verb and resource — transcribe speech from an audio file at a public URL — and pins the engine (Whisper large-v3-turbo), so the agent knows exactly what it gets. It does not, however, differentiate itself from the sibling ai_speech, leaving the agent to infer whether the split is speech-to-text vs text-to-speech.

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 concrete use cases (voice notes, podcast clips, meeting snippets, voice messages) plus a working example URL, which is clear context for when to reach for this tool. There are no exclusions or named alternatives, so it stops short of full when/when-not guidance.

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