transcribe_to_labels

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

With no annotations, the description carries the disclosure burden. It reliably discloses asynchronous behavior (immediate job_id return), the experimental status, setup requirements, and the need to clean up previous labels. It could further mention whether it uses selected audio or the entire project and whether it creates or reuses a label track, but the provided behavioral details are strong.

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 well-organized and front-loaded: purpose first, then setup, execution mode, cleanup guidance, and parameter explanations. Every sentence adds value, and the Args section is clean and easy to parse.

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 an experimental async tool with no output schema, the description covers the essential operational context: dependencies, background execution, job_id return, label cleanup, and parameter meanings. It does not mention how to track job completion or exactly which audio is transcribed, but enough information is present for an agent to invoke the tool correctly and know what to expect.

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?

The schema contains no parameter descriptions, yet the description fully documents all three parameters: model_size with specific Whisper model values, language with ISO code or auto-detect semantics, and task with transcribe vs translate behavior. This fully compensates for the 0% schema coverage.

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 description clearly states a specific action: 'Transcribe audio and add Audacity labels at each segment timestamp.' This distinguishes it from sibling transcription tools like transcribe_to_file or transcribe_audio by emphasizing label output, and the background/job_id behavior further differentiates it.

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?

The description provides practical context: it is experimental, requires a separate pip install, runs in the background, and explains how to clear stale label tracks before re-running. However, it does not explicitly contrast this tool with transcribe_to_file, transcribe_audio, or transcribe_selection, so an agent must infer when this tool is preferred over those alternatives.

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