transcribe_audio

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses that the tool is experimental, requires separate setup, runs in the background and returns a job_id, may fail, and can misdetect language. It also explains the expected user-facing behavior and retry strategy, far beyond what any schema or annotation supplies.

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 the core purpose and experimental caveat. The only minor issue is slight redundancy in the post-completion instructions ('TELL the user... Always tell the user...'), which could be tightened without losing meaning.

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?

Given no output schema and no annotations, the description is remarkably complete: it covers setup, execution mode, monitoring, failure handling, parameter usage, language pitfalls, and what to do after the job finishes. An agent has enough context to call the tool correctly and respond appropriately to results.

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 input schema provides no descriptions (0% coverage), but the description fully compensates by documenting each parameter: model_size with valid values and default, language with ISO examples and None for auto-detect, and task with 'transcribe' vs 'translate' semantics including the English-output behavior.

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 states a specific action and resource: 'Transcribe the entire project audio using faster-whisper (local, offline).' It also distinguishes this from related siblings by emphasizing 'entire project' and by explicitly referencing check_transcription_status and transcription_set_model, so an agent can identify the right tool.

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 explicit when-to-use and when-not-to-use guidance: it tells the agent to monitor progress with check_transcription_status, poll every 10-15 seconds, and warns 'Do NOT call transcription_set_model first.' It also gives post-call instructions for informing the user about the saved transcript and retrying with corrected language/task.

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