transcribe_audio

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

No annotations are provided, so the description carries the behavioral disclosure burden. It does reveal useful non-obvious behavior: segments feed a dubbing pipeline, video uploads return a video_id, and keep_background_music splits a music bed. However, it omits auth requirements, sync/async behavior, limits, and side effects, and the phrase 'unbilled draft' is unexplained.

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 definition is front-loaded with the main purpose, and each parameter gets a compact, useful line. The cross-tool pipeline note earns its place. The only blemish is the unclear parenthetical 'unbilled draft', which is jargon and not explained.

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?

An output schema exists, so return values do not need to be fully restated. The description already covers the dubbing workflow, video_id for muxing, and all parameter semantics. It is complete for typical use, though it does not mention file-size limits or supported language codes; these are minor given the available schema and sibling 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?

Schema description coverage is 0%, and the description compensates completely: file_path gives accepted audio/video formats, source_language_code is framed as an optional hint with an example, and keep_background_music has a behavioral consequence ('split a music bed for later remix'). This adds real meaning beyond the bare property names and types.

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 opening sentence names the exact operation ('Transcribe speech') and resource ('local audio or video file'), and the pipeline note clarifies the output usage with translate/synthesize_audio and video_id for muxing. This differentiates it from siblings like parse_audio_script or remux_video without needing to inspect their schemas.

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 gives a concrete workflow: use the returned segments with translate, then synthesize_audio to build a dubbed track, and video uploads return a video_id for muxing. It does not explicitly name alternative tools or say when not to use it, but the cross-tool pipeline context is enough to guide an agent.

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