transcribe

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the internal pipeline (ffmpeg resample to 16 kHz mono) and the return payload (segments plus word-level timestamps). It omits operational traits such as runtime cost, model availability failure modes, and any length limits.

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?

A single front-loaded sentence with no filler: the action, the backend constraint, the preprocessing step, and the return shape all appear in order of importance.

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?

With no annotations and no output schema, the description usefully covers both the processing behaviour and what comes back, which is the main gap a missing output schema creates. Remaining gaps are minor: no failure modes (e.g. missing ggml model file) and no performance expectations.

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 100%, so all four parameters are already documented in the schema. The description only echoes the backend concept and the word-timestamp output, adding no syntax, defaults, or edge-case meaning beyond the structured fields.

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 verb (transcribe) and resource (local audio or video file) plus the implementation (local Whisper backend, whisper.cpp or faster-whisper). It is clearly distinguishable from siblings like render or audio.mix, but it never explicitly contrasts with captions.generate, the closest neighbour.

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 repeated emphasis on 'local' implies the tool operates on on-disk files with an offline backend, which implicitly excludes remote/URL sources. However, there is no explicit statement of when to choose this over captions.generate, nor any prerequisite or exclusion guidance.

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