audit_site

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

With no annotations provided, the description fully discloses behavior: it is read-only, polices crawl rate (~1 req/sec), does not modify the site, and conditionally uses PageSpeed Insights. It details the types of checks and the structure of the response (summary and issues array), going well beyond typical descriptions.

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 comprehensive yet well-organized, with clear sections for different check categories. It front-loads the core purpose and every sentence adds value, avoiding redundancy. Despite length, it remains focused and structured.

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, no output schema, and three parameters, the description is remarkably complete. It explains the return schema in detail (per-pillar summary, issues array with fields like code, category, severity, etc.) and covers edge cases (e.g., conditional API key usage, redirect following).

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 100%, and the description adds meaning by explaining defaults (max_pages default 25, cap 100), conditions (speed_sample ignored unless API key set), and the expected format for site_url. This provides context beyond the schema's basic descriptions.

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 'READ-ONLY, platform-agnostic site auditor' and enumerates the audit categories (SEO, GEO/AEO, speed). However, it does not explicitly differentiate from sibling tools like `speed_audit` or `preview_fix`, though the comprehensive scope implies it is the primary audit tool.

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 explains that the tool works on any website and is read-only, providing clear context. However, it does not specify when to use this tool versus alternatives (e.g., `speed_audit` for speed-only audits), nor does it give explicit 'when not to use' guidance.

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