audit_siteCrawl a same-domain site to audit pages for SEO and technical issues, then summarize scores, common problems, and duplicate titles or meta descriptions.
Crawl a site from a start URL (same domain only), audit every page found, and summarize scores, the most common issues, and duplicate titles or meta descriptions.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Start URL, usually the home page | |
| max_pages | No | Maximum pages to crawl |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful context beyond that: the crawl is domain-restricted and capped by max_pages, and the output is an aggregate summary. It does not mention crawl cost/time, robots.txt handling, or failure behavior on unreachable pages, which is the main remaining gap.
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?
A single sentence with no waste; the input, the constraint, and the returned summary are all front-loaded in one pass.
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?
With no output schema, the description correctly takes on the burden of describing return values – scores, most common issues, duplicate titles/meta descriptions. That covers the essentials for a 2-parameter crawl tool, though crawl depth/limit behavior and error handling are left implicit.
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 both parameters carry their own descriptions, so the baseline is 3. The description only adds that the URL is the start point and that crawling stays on the same domain, which is meaningful but does not go beyond what the schema largely conveys.
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 specific verbs and resource: crawl from a start URL, audit every page, summarize scores/issues/duplicates. The scope markers 'same domain only' and 'every page found' make it immediately distinguishable from the sibling audit_page, which handles a single page.
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?
Usage is only implied – an agent can infer this is for whole-site auditing versus audit_page or check_links, but no alternative is named and no when-to-use/when-not guidance is given. The 'same domain only' constraint is the only explicit scoping rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.