audit_url

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

The description extensively details behaviors: rendering, scroll-settling, interaction firing, pixel/DOM capture, and rule engine execution. It also notes the requirement for headless Chromium. Annotations (readOnlyHint, openWorldHint, destructiveHint) are consistent and not contradicted.

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 informative but somewhat verbose. It front-loads the core purpose and then lists features, with every sentence adding value. However, it could be slightly more concise for quicker parsing.

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 complexity (9 parameters, no output schema), the description provides a thorough overview of functionality, including the nature of findings (confirmed/likely-artifact/inconclusive). It does not explicitly describe the output structure but gives enough context for an agent to understand what to expect.

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?

All 9 parameters have descriptions in the schema (100% coverage), and the description adds significant context beyond the schema. For example, it explains the purpose of 'compact' (drop base64 screenshots to save budget) and 'interactions' (diff against baseline for white-wash detection).

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 performs a 'Layer 0 render-and-capture audit' on a live URL, including scroll-settling, interactions, pixel capture, and various visual checks. It distinguishes itself from siblings by emphasizing it catches 'real-world visual nits invisible to HTML-string/geometry audits,' making its purpose specific and distinct.

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 implies when to use (for visual nits not caught by HTML-string audits) but does not explicitly state when not to use or name alternatives. However, it provides enough context for an agent to infer appropriate usage scenarios, given sibling tools like audit_page.

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