回复 / @ / 点赞通知

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is carried structurally. The description adds one useful behavioral distinction — kind=unread returns a count while the other kinds return lists — but says nothing about pagination behavior, auth requirements, or result volume.

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?

One sentence plus a compact kind-to-return mapping, front-loaded with the core purpose. Every clause carries information; nothing is 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?

With no output schema, the description usefully sketches what the unread and list kinds return, and 100% schema coverage handles parameters, so an agent can call it correctly. It stops short of describing the shape of returned notification items, which would have made it fully self-contained.

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%, so the baseline is 3; the description goes beyond the schema's terse '通知类型' by explaining the return meaning of each enum value, which materially helps the agent choose a kind. Pagination parameters (ps/page) are left to the schema.

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?

It states a specific verb+resource (读取 B 站消息中心通知) and enumerates what each kind returns, so an agent understands the tool's scope. It does not explicitly distinguish itself from the sibling 'messages' tool, which could plausibly overlap, so it falls short of a 5.

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?

Each kind value is mapped to its meaning (unread=未读数, reply=回复我的, at=@我的, like=收到的赞), which effectively tells the agent which selector to pick. There is no explicit when-not or named alternative, so it is strong context rather than full routing guidance.

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