Full technical SEO audit

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

Annotations already provide readOnlyHint and openWorldHint, but the description adds substantial behavioral detail: output formats (Markdown with ✅/⚠️/❌, JSON with severity and pas/warn/fail counts, HTML written to disk), baseline diff behavior via compare_to_baseline, and the explicit exclusion of Lighthouse. It also discloses that HTML output writes a file, which is a side effect beyond the read-only audit itself. No contradiction with annotations.

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 dense but every sentence earns its place. The first clause front-loads the purpose, the long checklist sentence is organized by category, and the remaining sentences cover output modes, baseline comparison, and exclusion. No filler or redundancy.

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 and the absence of an output schema, the description is thorough: it explains all output formats, baseline diffing, file-writing behavior, and the Lighthouse exclusion. It could add notes about URL accessibility/errors or explicitly state which sibling checks are included (e.g., whether keyword placement/URL structure are covered), but it is complete enough for an agent to select and invoke correctly.

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 input schema covers 100% of parameters with detailed descriptions, including the output enum, defaults, and output_path specifics. The description summarizes some of this (e.g., 'structured JSON with output: json', 'shareable HTML file with output: html') but does not add meaning beyond what the schema already provides. Baseline 3 applies.

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 uses a specific verb ('Run') and resource ('full technical SEO checklist on a URL'), enumerating concrete checks (rendering, HTTPS, page essentials, cache, structured data, etc.). It clearly distinguishes itself from the sibling individual checker tools by being the comprehensive 'full' audit, and it explicitly names run_lighthouse as a separate tool for Lighthouse.

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 tells the agent when to use this tool: when a full technical SEO audit is requested. It also provides an explicit exclusion and alternative: 'Does not include Lighthouse (use run_lighthouse separately — it is slower).' The sibling list of targeted check_* tools implies that for single-aspect checks, the individual tools are more appropriate, giving clear usage context.

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