bili_watch_video

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

With no annotations, the description carries the full burden and does well: it discloses that the job is asynchronous (poll bili_watch_status), that results report actual source coverage and gaps rather than overclaiming, and it enumerates hard limits (64MiB, 1 concurrent job, 3 API attempts/day, no Agent/schedule created). It does not describe failure modes or partial-failure behavior beyond the coverage caveat.

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?

Front-loaded with the core operation and the range constraint, followed by the async/limits facts. Nearly every sentence carries information; the closing 'Decide your interests and notes' is the one sentence that does little work.

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 5-parameter async job tool with no annotations, the description covers the essential unstated behaviors: async polling, honest coverage reporting, quotas, and no scheduling side effect. Return-value detail is legitimately omitted because an output schema exists; the remaining gap is parameter-level meaning for bvid/part/question.

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 coverage is 0%, so the description must compensate. It adequately explains start_seconds/end_seconds (explicit, continuous, max 180s, only needed for long parts) but says nothing about bvid, part (default 1), or the ambiguous 'question' parameter; 'Decide your interests and notes' is too vague to resolve what 'question' does.

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 concrete verb (perceive) plus resource (a complete short Bilibili part or an explicit start/end range of a long part) and specifies audio+video capture. That distinguishes it from metadata siblings like bili_video_info and bili_subtitle. 'Perceive' is non-standard phrasing, but the scope is unambiguous.

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 tells the agent to poll bili_watch_status after calling and states the 180s range cap, which is real operational guidance. It never says when to prefer this over sibling tools such as bili_video_info or bili_subtitle, leaving the choice to inference.

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