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

Adds behavior beyond the annotations: the call is asynchronous and returns before the crawl completes, it yields a job_id plus a shareable site_map link, and progress must be retrieved via get_crawl. That async contract is key context the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) do not convey. It does not mention job lifetime, timeouts, or cost implications, which keeps it at 4.

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?

Three short sentences, front-loaded with the action and the immediate-return behavior, followed by the polling instruction and plan note. No filler or redundant restatement of the title.

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?

Covers the essential contract for an async job tool: what is returned, how to follow up, and plan limits. With annotations present and an output schema documenting return values, the remaining gaps (job expiry, concurrency limits) are minor.

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 100%, with both url and max_pages documented including format and the 1-100 bound, so the schema carries the parameter burden. The description only indirectly informs max_pages via 'Same plans as crawl_site', adding marginal meaning. Baseline 3 is appropriate.

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 site crawl') and immediately qualifies the interaction model ('return immediately with a job_id and a shareable site_map link'), which distinguishes it from a blocking crawl and from the sibling get_crawl used for polling. An agent can tell what this tool does and how it differs without opening the schema.

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 explicit follow-up routing: 'Poll it with get_crawl' tells the agent the next step after this call. It also notes 'Same plans as crawl_site', which conveys entitlement/plan context. It stops short of stating when to choose this over crawl_site (e.g., 'use crawl_site if you want results inline'), leaving that inference to the agent.

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