audit_html

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description usefully reinforces that with "without network access". It also discloses the return character — evidence plus prioritized recommendations — which is valuable given there is no output schema.

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?

Two short sentences, zero filler, with the key constraint and the return shape both front-loaded. Nothing here can be trimmed without losing information.

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?

The description never says what dimension is being audited (accessibility, SEO, performance, security), and with no output schema the phrase "evidence and prioritized recommendations" is the only clue about returns. Adequate to invoke, but an agent cannot predict the findings' scope or structure.

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 coverage is 50%: `url` is documented as a base URL for relative links, but `html` has no schema description and its 2MB maxLength is undisclosed. The description's "supplied static HTML" only loosely implies the html parameter and adds nothing about size limits or how url affects link resolution.

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?

Specific verb+resource: "Audit supplied static HTML" clearly states what is acted on and that input is provided rather than fetched. The phrase "without network access" implicitly separates it from audit_url and crawl_site, though neither sibling is named, so differentiation requires inference.

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 constraint "without network access" implies this is the tool for already-retrieved markup, which is a usable selection signal against audit_url/crawl_site. However there is no explicit when-to-use statement, no exclusion, and no mention of what to do when only a URL is available.

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