扫描无效公式

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

With no annotations the description carries full burden and mostly succeeds: it declares 只读 (safe, no mutation) and discloses the detection rules — KaTeX for display math, bracket pairing only for database formulas, and API 'unsupported' results counted as broken. That framing matters because it tells the agent what the findings mean. Permissions requirements and any size/rate limits are not mentioned.

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?

Four short sentences, each doing distinct work: what is scanned, what is returned, the read-only guarantee, and the defect criteria. The result and safety statements are front-loaded where an agent will read them.

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 and no annotations, the description supplies enough: it says findings are a list of locations plus reasons. It stops short of describing the shape of that list (grouping, snippets, severity ordering), which an agent would want for a rich audit report.

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?

There is only one parameter and schema description coverage is 100%, with pageId documented as '页面 id 或页面 URL'. The description adds no further parameter detail, which is acceptable at this coverage level but earns only the baseline.

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 (检查/列出) and resource (行内公式、公式块、数据库公式属性), and enumerates what counts as a defect. It is clearly narrower than siblings like audit_page or audit_structure, though it never names them to make the separation explicit.

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 scope (page-level, formula-only, read-only) implies this is the tool for formula validation before rendering, but there is no explicit when-to-use guidance and no statement of when to pick audit_page or audit_structure instead. Inference is required.

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