transcribe_audio

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

With no annotations, the description carries the behavioral burden and does so well: experimental status, background execution, job_id return, local/offline dependency, required pip setup, and language auto-detection pitfalls are all disclosed. It does not cover failure modes or whether models need downloading, but the key async behavior is transparent.

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: core purpose and warning first, then workflow, then caveats, then a compact Args block. No sentence is redundant, and all operational details earn their place.

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?

The tool has no output schema or annotations, but the description is self-contained: it explains prerequisites, async behavior, monitoring, language caveats, and every parameter. An agent has enough to select, invoke, and follow up on the job correctly.

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 description coverage is 0%, so the description fully compensates by documenting all three args with allowed values, defaults, and semantics: model_size options, ISO language/None, and transcribe vs translate. This adds meaning the bare schema completely lacks.

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 operation: transcribe the entire project audio with faster-whisper, and clarifies it runs locally/offline. The phrase 'entire project audio' distinguishes it from selection/label/file-target transcription siblings without ambiguity.

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 workflow guidance: run in background, receive job_id immediately, poll check_transcription_status every 10-15 seconds, and pass language explicitly to avoid auto-detection errors. It does not explicitly contrast with transcribe_to_file or transcribe_selection, so no exclusions are stated.

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