Start Crawl

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-structured behavior: the call is fire-and-forget and returns an id without waiting, and results can overflow context. It does not mention that repeated calls spawn duplicate crawl jobs (relevant given idempotentHint=false) or any resource/credit cost, which keeps it short of a 5.

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 sentences, front-loaded with the async return contract, then the sibling routing, then the context-safety caveat and the alternative. No filler and nothing repeated.

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 still tells the agent what comes back (a crawl id) and how to retrieve the actual content later, and it covers the main hazard (context overflow) for a 9-parameter open-world crawl. Nothing needed to invoke it correctly is missing.

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 coverage is 100%, so all nine parameters are already documented and the baseline is 3. The description goes beyond the schema by explaining *why* `limit` is low by default (crawled content can overflow context), which changes how an agent should tune it rather than merely restating the default value.

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 website') and immediately defines the scope of the operation as asynchronous — it 'returns the crawl id right away, without waiting for it to finish.' It also distinguishes itself from crawl_status, crawl_results, crawl_cancel, and the map/scrape_as_markdown pair, so an agent can place it in the workflow without opening schemas.

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 when-to-use routing: check progress with crawl_status, read pages with crawl_results, stop early with crawl_cancel, and for precise work prefer map plus scrape_as_markdown. That is a complete lifecycle plus a stated alternative with the condition that selects it.

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