视频评论

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds genuinely useful behavior: which fields come back (pinned comment, like counts, IP location, hot sub-replies) and that pagination is offset-based. It does not mention rate limits or whether deep pagination is capped, which keeps it below 5.

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?

Three short sentences, front-loaded with the resource and the payload, then pagination, then provenance. The Bilibili-Evolved reference is the weakest sentence but does give implementation context; nothing else is padding.

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 output schema, the description carries the burden of describing return values, and it only sketches them rather than naming the cursor field precisely. It says '用 next_offset 翻页' while the schema's parameter is 'offset' and the cursor field is described there as 'nextOffset', an inconsistency that could make an agent guess at the pagination token's name.

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 50%; 'sort' and 'limit' have no schema descriptions at all. The description partially compensates by naming the two sort modes (热门/最新) and explaining that the offset parameter is fed from the previous response's cursor, but it never mentions the limit ceiling of 20 or the accepted input identifier formats.

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+resource (获取视频评论) and narrows scope with the sort modes (热门或最新) plus the data returned (置顶评论、点赞数、IP 属地、楼中楼). It is clearly distinguishable from most siblings, though it never explicitly separates itself from bili_danmaku, which an agent could plausibly confuse with 'comments'.

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?

Usage is only implied: an agent infers 'call this to read a video's comment section.' There is no statement of when not to use it, no prerequisite about needing a resolved video ID, and no pointer to bili_danmaku as the alternative for bullet comments.

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