get_seo_audit_report

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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, so the safety profile is covered. The description adds substantive behavior beyond that: no Google credentials required, JS execution in a guarded browser, sitemap discovery of unlinked candidates, crawl time and page-cap limits, query-string preservation, and robots.txt is respected by default.

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?

It is front-loaded with the core deliverable in the first sentence and each subsequent sentence adds a distinct operational fact. It is information-dense but not bloated, though a slightly tighter organization around parameters would improve scanability.

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 six parameters, no schema descriptions and the presence of an output schema, the description covers the behavioral and parameter essentials an agent needs: credentials, crawl bounds, robots policy, JS modes, sitemap behavior and comparison workflow. Return value details are appropriately left to the output schema.

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 0%, so the description must carry parameter meaning. It explains that max_seconds bounds the crawl, max_pages is capped by server configuration, respect_robots defaults on with a warning to disable only for controlled sites, and rendered/compare modes execute JS. render_mode values and several defaults are still not spelled out.

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 states a specific verb (return), the resource (structured technical SEO action plan with rule IDs, URLs, evidence, fix guidance, crawl coverage and limits), and distinguishes itself from siblings by naming compare_seo_audits. It is unmistakably the full-site SEO 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?

It gives clear workflow guidance: save the returned JSON for later comparison with compare_seo_audits, and notes that rendered/compare modes execute JS while include_sitemaps discovers nested sitemaps. It lacks explicit when-not-to-use advice versus similar siblings like crawl_site_seo or audit_live_site.

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