transcribe_start

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

With no annotations, the description carries full responsibility. It discloses background execution, immediate return of job_id, and a required prerequisite (npm run ui). While it omits error scenarios or cancellation, it covers core behavioral aspects well.

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 focused and not overly verbose. The inclusion of a three-step flow adds operational clarity, though it slightly extends length. Overall structure is logical 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?

Given the absence of an output schema, the description does specify the return object { job_id, cached, status, estimate_minutes }, which is helpful. However, it does not detail parameter meanings or handle edge cases, leaving gaps for an agent needing full context.

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 has zero description coverage, and the description does not explain any parameter individually (e.g., 'file_path', 'engine', 'language', 'model_size', 'num_speakers', 'enable_diarization'). Only 'file_path' is mentioned in passing within the flow, without elaboration.

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 the action (start transcription), the resource (transcription), and the return (job_id). Explicitly contrasts with sibling 'transcribe_podcast' for long files, making the tool's distinct purpose unambiguous.

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 guidance: 'Use this instead of transcribe_podcast for long files' and describes a detailed flow (call, emit status, poll job_status, read transcript via get_ui_state). Also gives performance expectations (60-min episode → 15–25 min) and a prerequisite (Web UI running).

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