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

Annotations set readOnlyHint=false, openWorldHint=true and destructiveHint=false; the description earns credit for explaining the non-read-only flag via 'kept for seo_set' (results are persisted), and for disclosing the free/cost profile and the 60-page cap. It omits crawl duration, caching/re-run behavior, and failure handling for unreachable sites.

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 and scope before the long extraction list, and it is a single efficient sentence. The middle enumerative clause is dense and reads like a checklist, but each item adds real signal about what the crawl checks.

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 no-parameter, no-output-schema crawl tool, the description carries nearly the full weight and does so by enumerating the outputs an agent would otherwise have to guess. Remaining gaps are runtime expectations and exactly how the stored results are consumed by seo_set.

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?

There are zero parameters, so the baseline is 4. The description consistently implies the target site comes from the workspace/record context rather than an argument, which is useful, but it never states this explicitly.

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 ('Read every page in the sitemap') plus a precise scope cap ('up to 60', prioritized by search visibility). It then enumerates exactly what is extracted (status codes, noindex/canonicals, title/H1 issues, thin pages, broken links, CWV, AI-answer page coverage), making it unmistakable versus siblings like seo_read or index_status.

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?

Signals when it fits into the workflow — 'Free; kept for seo_set' tells the agent this is the free collection step whose results feed a later setter. It does not explicitly state when NOT to use it or name seo_read as the lighter alternative, so it falls short of full routing guidance.

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