Full technical SEO audit

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

Adds real behavioral context beyond the annotations: the report can be Markdown/JSON/HTML, HTML writes a file, and compare_to_baseline both diffs and updates a saved baseline. This matters because readOnlyHint=false and openWorldHint=true are consistent with a tool that fetches a URL and writes state. No contradiction, but it doesn't quantify cost/rate limits.

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?

Front-loaded with the action and scope, then output formats, baseline behavior, and the Lighthouse exclusion. It is a single dense paragraph and the checklist enumeration is long, but nearly every clause carries usable information rather than filler.

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?

For a complex, many-check aggregator with no output schema and 4 parameters, the description discloses the checks performed, all three output modes, baseline diffing, and the one sibling boundary that matters. An agent has everything needed to call it 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?

Schema description coverage is 100%, so every parameter (url, output, output_path, compare_to_baseline) is already documented in the schema, including the HTML-on-disk behavior and default path. The description largely restates these ('output: json', 'output: html', compare_to_baseline), so baseline 3 is appropriate.

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?

States a specific verb and resource ('Run the full technical SEO checklist on a URL') and then enumerates exactly what is covered (rendering, HTTPS/redirect, page essentials, caching, structured data, sitemap, robots, AI-crawler access). This makes it immediately distinguishable from the individual check_* siblings, which it subsumes.

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?

Explicitly excludes Lighthouse and routes the agent to run_lighthouse separately, with the reason ('it is slower'). It also names the compare_to_baseline trigger. It does not explicitly state when to prefer this aggregate audit over the individual check_rendering/check_https/etc. siblings, so it stops short of a 5.

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