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

Annotations already supply non-idempotent and destructive hints, and the description reinforces and extends them: repeated pinning changes the timestamp, there is no recovery entry after unpinning (无恢复入口), hidden messages cannot be pinned, and true may surface the message on the big screen. It also explicitly forbids automatic retry on unknown failures, which is behavioral guidance annotations cannot express.

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 requester/role banner 【需登录·本场主办方】 is front-loaded, and every clause (prereq, semantics, constraint, failure policy) carries information. It is dense and clause-stacked with little whitespace, which slightly taxes scanning, but there is no filler to cut.

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-param mutation tool with full schema coverage and annotations covering the safety profile, the description closes every remaining gap: who may call it, what to verify first, what true vs false do, what is irreversible, and how to react to an unknown failure. No output schema exists and none is needed for this action.

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 100%, so baseline is 3; the description partially mirrors the schema's true/false definitions but adds the consequence that a true pin '可能上大屏' (may reach the big screen) and that a false pin does not hide the message. That consequence is decision-relevant and not present in the schema, though the parameter syntax itself is still 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?

The description conveys pin/unpin semantics through its true/false branches ('true替换本场置顶', 'false仅撤该消息置顶') and makes the scope explicit as this specific live session. It also implicitly distinguishes itself from hide_live_message ('不隐藏'), so an agent can separate the two. However, it never states the core action in a standalone clause and leans on the tool name/title to do that work.

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 explicit prerequisites (requires login, must be the session organizer), a named verification step ('先get_organizer_live核对作者/messageId/全文'), and a hard exclusion ('隐藏消息不能置顶'). Failure-path guidance ('未知失败先核对主持台，禁止自动重试') further routes the agent on what to do when the call is ambiguous.

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