scan_site

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

With no annotations, the description does real work: it discloses robots.txt compliance, sitemap.xml discovery, and that results are cached for other tools. It omits important operational traits such as runtime/timeout expectations, whether the crawl is breadth- or depth-limited, handling of JS-rendered sites, and whether caching means repeat calls are free.

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?

One dense, front-loaded sentence where the crawl action, the governing behaviours, and the returned artefacts each appear in that order. No filler; slightly long clauses are justified by the information they carry.

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?

There is no output schema and no annotations, yet the description still enumerates return contents well enough to plan around (profile fields, per-page SEO, broken links, link stats). The remaining gap is crawl-scope behaviour tied to max_pages and what a cache hit looks like for the caller.

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 0% and the description never mentions either parameter. 'url' is obvious from the name, but 'max_pages' (default 30) — the key control over crawl cost and completeness — is left entirely unexplained, so the description fails to compensate for the empty schema.

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 concrete verb+resource ('Crawl a live website') and enumerates the outputs it produces (business profile, per-page SEO data, broken links, link stats). It doesn't explicitly contrast with near-neighbours like scan_codebase or seo_link_audit, so the sibling differentiation is only inferable from 'live website'.

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 implied rather than stated: 'Results are cached for the other tools' hints this is the first-step scan whose output downstream tools consume, but there is no explicit when-to-use/when-not guidance and no named alternative (e.g. scan_codebase for source, recheck_live_links for a re-check).

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