transcribe_audio

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

No annotations exist, so the description carries the full burden and it falls well short. 'Cost is not estimated locally' gestures at billing risk but never explains the allow_paid / allow_unknown_cost gating, what happens when a paid model is requested without opt-in, or that the tool writes a transcript file to disk (filename defaults to transcript.json) and whether it overwrites.

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 short sentences with the core action front-loaded and no filler. The closing sentence about cost is terse to the point of being cryptic, but nothing is redundant.

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?

A 10-parameter transcription tool with no annotations, no output schema, and no schema descriptions needs a far richer definition. The description omits the paid-operation safeguards that are the main invocation risk, does not explain the file-writing side effect, and says nothing about return values.

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%, so every one of the 10 parameters depends on the description for meaning. It only alludes to three (model_id, diarize, timestamps_granularity) in a single summary clause, leaving the two cost-safety booleans, language_code, num_speakers, tag_audio_events, input_path and filename entirely uninterpreted.

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?

The first sentence gives a specific verb and resource ('Transcribe a local audio or video file') and the word 'local' implicitly separates it from retrieval-oriented siblings like get_transcription or transcript_to_subtitles. It stops short of naming an alternative, so an agent must infer the boundary itself.

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?

There is no statement of when to call this versus get_transcription, align_audio_to_text, or estimate_cost, and no prerequisites or exclusions are given. The only usable cue is the phrase 'local ... file', which hints at the input scope but is not framed as guidance.

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