结束抓取并汇总

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

No annotations exist, so the description carries the full burden. It usefully discloses the non-persistent behavior ('不落盘') and the return content, but says nothing about prerequisites (must a capture be running?), error/empty conditions, or what the returned summary contains operationally.

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 short sentence with the primary action front-loaded, followed by the persistence caveat in a parenthetical. Nothing is wasted and the key differentiator is not buried.

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 annotations, no output schema, and four undocumented parameters, the description is only partially sufficient: it explains scope and persistence but leaves both the parameter meanings and the nature of the returned 'suggestion summary' unexplained.

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?

All four boolean parameters (includeDom, includeStorage, includeScreenshot, includePerformance) have 0% schema description coverage and are completely unmentioned in the description. The agent cannot learn from either source what toggling these flags changes in the returned statistics.

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 and resource ('结束当前这一轮抓取') plus the return payload ('统计与建议摘要'), and explicitly names the sibling it is not ('要落盘用 capture_save'). An agent can separate it from capture_start/capture_save/capture_status without opening any schema.

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?

Gives one explicit routing rule: use capture_save when persistence is required. It implies usage after a capture round, but never says when to prefer this over capture_status or what state (an active capture) must hold before calling.

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