crawl

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

No annotations exist, so the description carries the burden. It discloses async behavior, immediate job id return, per-page cost, budget refund, and output format (Markdown). Does not mention potential side effects like rate limits or data retention, but covers the key operational traits.

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?

Concise single paragraph, front-loaded with action and resource, then key details on costs and alternatives. No fluff, but could be slightly more structured (e.g., separating usage guidance).

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?

Description covers the async nature, job id, cost, and alternative tools. It does not explain parameter semantics, but schema does. No output schema provided; description mentions 'poll with crawl_status' so return behavior is clear. For a complex tool, it's reasonably 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?

Input schema already provides full descriptions for all 8 parameters (100% coverage). The description does not add parameter-specific meaning; it only clarifies the overall outcomeщаться, which is adequate given high schema coverage.

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?

Description clearly states it starts an asynchronous BFS crawl from a seed URL, returns Markdown, and explicitly contrasts with map/batch for filtered URL lists, distinguishing it from siblings.

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?

Explicitly advises 'Prefer map + batch when you can filter the URL list first,' and notes the async nature with polling via crawl_status. Clear when-to-use and alternative guidance.

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