transcribe_audio

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

Despite no annotations, the description discloses experimental status, background execution, immediate return of job_id, required polling interval, automatic model loading, and file output. Could mention potential resource usage or cancellation, but overall satisfactory.

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?

Well-structured with experimental tag, purpose, setup, error handling, background details, important note, and args. Slightly verbose but every sentence adds value. Could be tightened slightly.

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?

Complete for the tool's scope: covers setup, error handling, asynchronous behavior, monitoring via sibling tool, and post-completion action. No output schema needed as tool returns job_id and saves file. No gaps identified.

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 0%, but description fully explains each parameter: model_size with options, language with ISO codes or null, task with transcribe vs translate effect. Adds meaning beyond the schema's defaults and types.

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?

Clearly states it transcribes the entire project audio using faster-whisper, distinguishing it from siblings like transcribe_selection, transcribe_to_labels, and transcription_set_model. The experimental nature and offline execution are highlighted.

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?

Provides explicit when-to-use (entire project transcription), prerequisites (separate setup), error handling (point to docs), background behavior (returns job_id, poll 10-15s), and warns against calling transcription_set_model first. Also advises telling user the output location.

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