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

Annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false) already convey the safety profile, so the description is free to add the operationally important details it does add: no credit consumption, the fetched video is persisted into the user's asset library (explaining why it is not read-only), the returned fields (video_url, cover, duration, title, author), and a rights caution against republishing others' work. It stops short of describing failure modes for unsupported/private links.

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 tool description is a single efficient clause, and the schema-level guidance is front-loaded: trigger → what it returns → where to pass it → what not to do. Dense but every sentence carries a decision-relevant fact; only the repeated negative instruction about not fetching platform pages yourself is mildly redundant.

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 1-parameter, no-output-schema tool, the definition covers the trigger conditions, the exact return contract, the persistence side effect, the credit cost, the downstream routing, and the legal/ethical usage constraint. There is no output schema, so describing the return payload here is the right call, and nothing an agent needs to invoke this correctly is missing.

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% for the single `urls` parameter, including the non-obvious behavior that an entire pasted share blob is accepted and the link is auto-extracted, plus the max-5 / min-1 bounds. The description text adds no parameter meaning beyond the schema, so the baseline 3 applies.

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 one-line tool description gives a specific verb+resource pair (解析平台视频链接，换取可用的视频素材) — parse a platform share link and return usable video material. It does not itself distinguish this tool from siblings; that differentiation only appears in the input-schema description, which names ad_clone_analyze / video_analyze / video_translate / video_subtitle as the downstream consumers. Clear purpose, but the routing signal lives outside the description field.

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 schema-level description enumerates the exact trigger (share links or copied share text from 抖音/TikTok/YouTube/Instagram/小红书/视频号) and states when NOT to call it (already-directly-downloadable .mp4 links). It also names the alternatives and the correct handoff: pass the returned video_url to ad_clone_analyze, video_analyze, video_translate, video_subtitle instead of sending platform links to those tools. Explicit when/when-not/alternatives.

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