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

The annotations already declare readOnlyHint=false and idempotentHint=true. The description adds specific behavioral detail: reading has a side effect (marking zombie rounds as FAILED) and explains the server-side 5-minute deadline. It also clarifies that READY means computed but not visible to attendees. This goes beyond annotations but doesn't fully cover every behavioral nuance (e.g., exact return format), though it's strong for a read operation.

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 description is well-structured with clear sections (需要登录·主办方, 何时用, 组合链, 口径), each sentence delivers actionable information without redundancy. It is front-loaded with the core purpose and usage, and the formatting makes it easy for an agent to parse.

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?

Despite lacking an output schema, the description explicitly lists the data fields returned (分组名、分组理由、话题、每组成员、报名/签到分母). It also explains the state machine, side effects, and the publishing requirement, which is critical for correct usage. For a single-parameter tool with rich workflow context, this is complete.

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?

The schema description coverage is 100%, and the schema already explains activityRef as an activity slug or id with pointers to other tools. The description does not add any additional parameter information beyond what the schema provides, so the baseline of 3 is appropriate. No extra semantics are needed.

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 clearly states what the tool does: it retrieves the latest Match Time round including group names, reasons, topics, member lists with attendance, and signup/check-in denominators. It also mentions the intended use case (turning into host scripts), which makes the purpose specific and unambiguous. It differentiates itself from siblings by naming the specific workflow it belongs to.

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 description explicitly provides 'when to use' (看 Match Time 最新一轮), the exact sequence with sibling tools (start_activity_match_round → poll this tool → publish_activity_match_round), and conditions like polling behavior when status=COMPUTING. It also includes detailed '口径' rules (e.g., FAILED must be reported as-is, READY requires publishing), leaving no ambiguity about when and how to use it versus alternatives.

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