audio_transcribe

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

With no annotations, the description carries the full burden and does so well: it discloses data handling ('the audio is deleted after the call'), hard limits (10 minutes / 24 MB per call), pricing ($0.01 USDC per call), latency (p99 60000ms), and the default/speed model tradeoff. These are exactly the traits an agent needs and cannot get from the schema.

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 the purpose and packs limits, cost, and return shape into a compact block. The opening 'Speech to Text (Whisper Transcription) — Speech to text for agents' restates the same idea twice, which is minor waste but the only real redundancy.

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?

No output schema exists, and the description compensates by naming the return payload (text, detected language, duration, segments with start/end seconds). Combined with formats, limits, model options, cost and latency, an agent has everything needed to invoke it 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 baseline is 3, but the description adds meaning beyond it: the language auto-detect behavior (~100 languages), the mutual-exclusivity framing of audio_url vs audio_base64, and the supported container formats (mp3, mp4, m4a, wav, ogg, webm, flac). It stops short of richer per-parameter detail, so not a 5.

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?

Opens with a specific verb+resource ('transcribe ... into text with timestamps') and names the concrete input types (voice note, meeting, podcast, call recording) and the engine (OpenAI Whisper). It is unmistakably distinct from siblings like tts (opposite direction) or language_detect.

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 clear context for use ('Speech to text for agents') and names an alternative access path (OpenAI-compatible POST /v1/audio/transcriptions). It does not, however, state when NOT to use it or route the agent to a sibling tool, so it falls short of the 5 bar.

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