Crawl site

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true. The description adds the important behavioral trait that the crawl is async and returns a job id for polling, which informs the agent about the non-immediate nature and required follow-up. This goes beyond what annotations alone provide.

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?

Two sentences with no superfluous text. The first sentence states the action and output, the second ties it to the sibling tool for follow-up. Every word earns its place.

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?

Despite having 7 parameters and no output schema, the tool description covers the key context: async nature, job id return, and polling via a specific sibling. It does not explain the crawling scope or error handling, but the input schema fills in parameter details. For a start-crawl tool, this is fairly complete.

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% (all 7 parameters have descriptions). The tool description does not add any additional parameter semantics beyond the schema, so baseline score of 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?

The description uses a specific verb ('Start') and resource ('async site crawl'), clearly states the output (job id), and distinguishes from the sibling tool crw_check_crawl_status by indicating the polling workflow.

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?

The description provides clear context for usage: start a crawl then poll with the sibling tool. It does not explicitly list when to avoid using it or compare with other siblings like crw_map or crw_scrape, but the implication is strong enough for a straightforward tool.

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