web_crawl

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: breadth-first strategy, same-host default, and 50-page cap. It does not mention robots.txt compliance, rate limiting, or error handling, leaving some transparency gaps.

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, no fluff, front-loading the most critical information about the crawl strategy and constraints. Ideal conciseness.

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?

Given no output schema, the description should at least hint at what is returned (e.g., extracted text or page data). It only mentions 'fetching and extracting each page' without specifying output format. Also, no mention of error handling or edge cases, leaving the agent somewhat in the dark about what to expect.

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 0%, yet the description does not explain any of the 4 parameters. While it hints at the 'same_domain' parameter by saying 'stays on the start host by default', it fails to clarify 'start_url', 'lang', or 'max_pages'. This is a significant gap.

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 performs a breadth-first crawl from a start URL, fetching and extracting each page. It also distinguishes itself from sibling tools by mentioning it stays on the start host by default and is capped at 50 pages.

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?

Description mentions default behavior of staying on the start host and page cap, implying usage for multi-page scraping within a domain. However, it lacks explicit guidance on when to use this tool versus alternatives like web_fetch or web_extract, and does not state prerequisites or exclusions.

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