transcribe_to_labels

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

With no annotations, the description carries full burden and discloses: experimental stability, setup requirements, async background execution, immediate job_id return, and monitoring mechanism. Minor gap on error handling or cancellation behavior prevents a 5.

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?

Every sentence serves a distinct purpose: stability warning, core function, prerequisites, execution behavior, workflow integration, and parameter docs. No redundancy, well front-loaded with critical flags like [EXPERIMENTAL] and BACKGROUND.

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 a complex async tool with no output schema, the description adequately covers the job lifecycle (submission via this tool, monitoring via sibling). Minor gap regarding which audio/track is targeted (selected? entire project?) prevents a perfect score.

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 has 0% description coverage, but the Args section fully compensates by explaining model_size options (Whisper model sizes) and language format (ISO code or None for auto-detect), providing complete semantic meaning for both parameters.

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 specific action ('Transcribe audio') and distinct output ('add Audacity labels at each segment timestamp'), clearly differentiating from siblings like transcribe_to_file or transcribe_audio. The [EXPERIMENTAL] prefix additionally sets appropriate expectations.

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?

Explicitly names prerequisite ('Requires separate setup'), execution model ('Runs in BACKGROUND'), and directly references sibling tool check_transcription_status for monitoring progress, providing complete workflow guidance.

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