crawl_url

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

Discloses that content is marked untrusted and scanned for prompt-injection, and lists supported formats. However, no annotations provided, and description fails to mention important behaviors like redirect handling, timeouts, error responses, or mutation. With zero annotation coverage, the description should be more thorough.

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?

Description is very concise (3 short lines), front-loads purpose. However, it omits parameter details, which would be necessary for completeness. Appropriate length but at expense of utility.

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 13 parameters and an output schema, the description is too brief. It doesn't explain caching, output format options, or parameter behaviors. Even with output schema existing, agent needs more context to set parameters correctly.

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 description must compensate but does not explain individual parameters. Only 'automatic escalation' relates to render_mode; other 12 parameters are not described. The schema properties' names provide some hint, but description adds little meaning.

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 action (fetch and extract), resource (one URL), and methods (HTTP, browser, auto). Distinguishes from siblings like crawl_site and extract_links by specifying single URL extraction and supported formats.

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?

No explicit guidance on when to use this tool vs siblings. Although 'one URL' implies single page extraction, no mention of when to prefer this over extract_links, parse_url, or browser_interact.

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