audit_surface

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 discloses a key behavioral trait: the report 'declares the axes a static check cannot judge rather than reporting them clean,' providing honesty about limitations. It also mentions fetching served HTML, implying a network request. It doesn't discuss safety or side effects, but as an audit tool, the implied read-only nature is acceptable.

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 two sentences, front-loaded with the core purpose, and each clause adds value. It lists the six axes compactly and explains the output behavior without redundancy. No wasted words.

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?

Given no output schema, the description appropriately outlines the return value ('per-axis report') and its honesty about unjudgeable axes. It covers inputs and output behavior. It references 'MISSING conformance auditor' without explanation, but that's a tool-specific detail. The absence of rate limits or auth notes is minor for an audit tool, and complexity is low with only two string parameters.

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 only defines url and html as optional strings with no descriptions. The description adds meaning: 'Pass a url to fetch and audit the served HTML, or pass html directly.' This explains the semantics of each parameter and their mutual exclusivity (implied by 'or'). It doesn't cover edge cases like providing both or none, but for two simple parameters this is adequate.

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 the tool audits a 'shipped web surface' across six specific axes with the MISSING conformance auditor. The verb 'audit' and resource are precise, and the listed axes distinguish it from narrower siblings like audit_findability or audit_delivery.

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 explicitly explains how to invoke the tool: pass a url to fetch and audit, or pass html directly. This gives clear input guidance. However, it doesn't explicitly contrast with sibling tools (e.g., when to use this general audit vs audit_findability), though the scope (all six axes) implies broader use.

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