美化后对照

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

No annotations are provided, so the description carries the full burden. It states '只读' (read-only), which is a key behavioral trait, and defines what counts as a factual change, but omits details about permissions, rate limits, or output format.

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 sentences, front-loaded with the core comparison task, followed by detection scope, exclusions, and read-only status. No fluff; every sentence earns its place.

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?

Covers the purpose and detection scope well, but lacks explanation of the return format (especially since there is no output schema) and does not describe the pageId parameter. For a diff tool, an agent would benefit from knowing how issues are reported.

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 50%. The description clarifies that 'snapshot' comes from apply_plan, but leaves 'pageId' completely unexplained and does not detail the expected snapshot structure. It only partially compensates for the schema gap.

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 ('对照' / compare) and resources (snapshot from apply_plan vs current page content), and clearly defines the two problem classes it detects, plus exclusions. This distinguishes it from generic audit tools like audit_page or audit_formulas.

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?

Implies usage after apply_plan produces a snapshot, but does not explicitly state when to use this tool versus alternatives such as audit_formulas or audit_page. No when-not guidance is provided, though the read-only note is helpful.

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