audio_transcribe

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

Annotations declare readOnlyHint and openWorldHint, but the description adds traits they don't cover: local execution (no cloud API call) and the first-use model download, which is a real latency/network side effect an agent should anticipate. It also discloses the return envelope in detail (segments, per-word confidence, detected language, pauses, uncertain_words).

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?

The purpose is front-loaded in a five-word lead, then parameter hints are packed into dense, colon-delimited clauses with no filler. It is slightly compressed, but 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?

For a 7-parameter tool with no output schema, the description covers the important behavioral facts and most parameters, and its return-value enumeration substitutes for the missing output schema. Remaining gaps are minor: what `path` accepts (local file vs URL) and whether timings are seconds or offsets.

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 0% and the model parameter has no enum, so the description carries the load: it enumerates valid model values (tiny/base/small/medium/large-v3/turbo) with a size-versus-speed tradeoff, and explains model, language, initial_prompt, start and end. Only path is left undefined, and word_timestamps is only implied via the mention of per-word timings.

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 ("Speech to text") plus the engine (Whisper) and an execution constraint (runs locally), so an agent immediately knows what this does and how it differs from audio_synthesize or audio_analyze. It also enumerates the outputs it produces, removing any ambiguity about scope.

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?

It gives per-parameter usage hints ("Use start/end to transcribe part of a long recording", "language: ISO code like \"en\" to skip detection") which is genuine decision guidance at the argument level. However, it never says when to pick this tool over siblings such as audio_batch_process for multi-file work or audio_analyze, so tool-level selection is only implied.

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