site_crawl

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds real value beyond that by disclosing recursive link-following and the shape of returned per-page data (title, meta description, headings, issues), but says nothing about crawl duration, throttling, robots.txt handling, or partial-failure behavior — all material for an open-world crawl.

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 core action, then use cases, then return shape, then args — a logical ordering with little filler. The Args block is partly redundant with the schema, though it does carry the otherwise-undocumented max of 100, and the provider tag is a single useful token.

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 spends a sentence on what comes back per page, and it covers both parameters including the undocumented cap. It falls short only on operational details an agent would want before launching a site-wide crawl, such as expected runtime, throttling, or how failures on individual pages are reported.

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 carries the burden and does compensate: it gives a URL format example and states max_pages defaults to 50 with a ceiling of 100 — the 100 cap is not present in the schema at all. Remaining gaps are minor, such as whether max_pages counts the start URL or how depth is bounded.

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 ('Crawl a website and return data for every discovered page') plus the recursive-link behavior, so an agent knows exactly what the operation does. It does not name or differentiate itself from plausible siblings such as site_map, batch_scrape, or content_scrape, which keeps it short of a 5.

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?

Lists concrete triggering scenarios: site-wide audits, content inventory, internal link analysis, orphan-page discovery, missing meta tags. That gives an agent a clear sense of when this is the right call, but there are no exclusions and no explicit pointer to a cheaper alternative for single pages or sitemap-only needs.

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