crawl

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

With no annotations, the description carries the full burden, and it does disclose key behavior: the crawl runs asynchronously in the background, returns a job id, and is terminated early by a query. It omits cost/rate implications of parallel workers, whether re-crawling is safe, and what the job result contains.

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 job-id return, then scoping rules, in about three dense sentences with no filler. Minor awkwardness in 'workers pages at once' where 'number of concurrent pages' would read more precisely.

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?

Ten parameters, no annotations, no output schema, and zero schema descriptions demand far more of the prose than is delivered. The description never explains default limits, depth semantics, format selection, or path filters, so an agent cannot call it confidently beyond the simplest case.

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%, so all 10 parameters depend on the description, yet it only explains strategy values, workers, entire_domain, and query behavior. url, limit, max_depth, formats, exclude_paths, and include_paths — over half the parameters — get no meaning at all, leaving defaults like limit=20 and max_depth=2 unexplained.

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 crawling a site in the background') and clarifies the async model by saying it returns a job id for crawl_status. It does not explicitly contrast with scrape or map_site, so an agent must infer why it would pick crawl over a single-page scrape.

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 useful in-tool guidance: default scope is under the start address, entire_domain widens to the whole site, and a query makes it stop once pages cover the topic. It never states when to prefer scrape, batch_scrape, map_site, or deep_research instead, which is the main gap given the crowded sibling set.

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