video_audio

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

With no annotations, the description carries the burden and does so well: it discloses local model execution (SenseVoice), that only the segment is downloaded (~0.5MB per 20s), that beat values are approximate, and that emotion/event outputs are model labels rather than facts. It omits cost/rate limits and response structure details beyond the label list.

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 compact and front-loads what the tool returns, then adds the download-scope and interpretation caveats. Each sentence contributes, though the caveat about beat estimation is slightly wordier than needed.

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 4-parameter tool with no output schema, the description conveys what the response contains and how to interpret it, which is the main thing an agent needs. The remaining gap is parameter-level detail (start/end/lang semantics), which is the only reason it is not a 5.

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 must document url, start, end, and lang. It only hints at the segment concept and the 20-second default ('20 秒约 0.5MB'); start/end formats and especially the purpose of the lang parameter (default 'zh') are left completely unexplained.

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 description gives a specific verb ('听一段' — sample a segment) and enumerates the outputs: SenseVoice language/emotion/audio events plus beat/energy. It also distinguishes itself from the transcription path by stating it '不转写全片', so an agent can separate it from video_subs/video_full, though it doesn't explicitly name those siblings.

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?

It gives clear conditions for when the tool is worthwhile (music or edit rhythm) and when it is not ('节拍估计对纯语音段意义有限'), which is real when/when-not guidance. It stops short of naming an alternative tool, so it is not a full 5.

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