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

Annotations already cover the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false). The description adds genuinely useful behavior beyond that: it returns a crawl id immediately (asynchronous start) and stops at the plan page cap, which explains partial results. The orphan not_measured edge case is a nice detail.

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?

Four short, front-loaded sentences with no filler; the purpose leads and the constraints follow. 'Does NOT crawl the whole internet' is slightly obvious but does earn its place as scope bounding.

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 helpfully explains the return value (crawl id) and the async nature. However, for a tool whose schema documents zero parameters, the absence of any parameter guidance leaves the definition incomplete for correct invocation.

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 explains none of the three parameters. 'pages', 'site_id', and 'allow_subdomains' are left entirely undefined, and the vague reference to a 'plan page cap' does not clarify how 'pages' relates to it. This is a real gap the description should have filled.

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 ('Start a multi-page crawl of a site') and bounds scope by declaring what it does NOT do (keyword/rank checks, whole-internet crawling). This lets an agent distinguish it from audit_page and check-related siblings, though no sibling is named explicitly.

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?

Gives a clear precondition ('a site you own') and explicit exclusions ('Does NOT run keyword or rank checks'), which helps an agent route keyword/rank work elsewhere. It stops short of naming the alternative tool or stating when to prefer this over audit_page.

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