transcribe_to_file

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

With no annotations provided, the description carries the full burden, and it delivers: marks itself experimental, requires setup, runs in the background returning a job_id immediately, rejects an existing file at the specified path, and warns that language auto-detection can misidentify language. This is candid about side effects, asynchronous behavior, and known failure modes.

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 description is long but information-dense and front-loaded with purpose, setup, mandatory path behavior, background behavior, and a nuanced language failure mode before the parameter list. Each block carries a distinct instruction; the structure makes the hard rules (ALWAYS, NEVER, BACKGROUND) stand out.

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?

It covers setup, path resolution, asynchronous execution, monitoring, retry behavior, file conflicts, and all parameter semantics, and references the relevant helper siblings. The main gap is that it never explicitly states which audio source is transcribed (current selection, whole project, or supplied audio), and there is no output schema or job-polling contract beyond pointing at check_transcription_status.

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 the description fully compensates: path is explained as an absolute output path, format gets its allowed values, model_size lists Whisper variants, language is described as ISO code or auto-detect, and task distinguishes transcribe vs translate output. This gives an agent everything needed beyond the bare schema.

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?

States a specific action and deliverable: 'Transcribe audio and export to a subtitle or text file.' This distinguishes it from sibling transcription tools like transcribe_to_labels (labels) and implies file output rather than in-memory/transcript-only results.

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 operational rules: always reveal save destination first, resolve unspecified paths via get_default_export_folder, never guess paths, monitor progress with check_transcription_status, and retry with a corrected language/task. It does not explicitly name transcribe_audio/transcribe_selection as alternatives or state when not to use them, so it falls just short of full alternative-selection guidance.

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