audit_html

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

Without annotations, the description must disclose behavioral traits. It explains the rendering process (headless Chromium, no network fetch) and the auditing by chosen engines. However, it does not explicitly state that the tool is read-only/non-destructive, nor does it mention failure modes or limitations for invalid HTML.

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 concise and well-structured: a one-line summary, a brief technical explanation, and a bulleted Args list. Every sentence adds value with no redundancy, and the key information is front-loaded.

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 the tool's complexity (5 parameters, no annotations, present output schema), the description covers the core functionality, parameter details, and common use case (CI). It omits the output format, but the output schema likely covers that. Overall sufficient for agent decision-making.

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?

With 0% schema description coverage, the description compensates by listing all parameters with types, defaults, and allowed values. It adds context for 'steps' by referencing audit_url, and clarifies engine defaults and subset. This adds meaning beyond the schema titles.

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 starts with a specific verb ('Audit') and resource ('raw HTML string or component snippet'), immediately distinguishing it from sibling tools like audit_url or audit_current_page. It further clarifies the scope by mentioning WCAG 2.2 and headless Chromium rendering.

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 description states it is 'Useful for testing templates/components in CI', giving a usage context, but does not explicitly compare to alternative tools or specify when not to use it. Lacks exclusion criteria or guidance on choosing between siblings.

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