Extract structured data

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

Discloses async behavior and LLM dependency beyond annotations. Annotations indicate mutation (readOnlyHint=false) and open world, which are consistent. The description adds context but could detail side effects or rate limits.

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 short sentences with clear front-loading. Every word serves a purpose: action, method, async polling, LLM requirement. No redundancy.

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?

Adequate for a complex tool with 6 params and no output schema. Covers core mechanism but lacks detail on return value, error handling, and comprehensive parameter guidance. Could better address the LLM dependency specifics.

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 67%, and the description mentions the two key parameters (prompt, schema). It does not elaborate on the LLM-related parameters (model, key, provider), which are critical. The description adds some value but not enough to fully compensate.

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?

The description clearly states the primary action: 'Extract structured JSON from URLs' with specific methods (prompt and/or JSON schema). It distinguishes from sibling tools like crw_scrape and crw_crawl by emphasizing structured extraction and async polling.

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?

Provides essential usage guidance: async nature requires polling via crw_check_extract_status, and an LLM is needed. However, it does not explicitly state when to use this tool versus alternatives like crw_scrape or crw_crawl.

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