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

Annotations already mark the tool as read-only, open-world, and non-destructive. The description adds meaningful behavioral context: output is validated against the schema, missing fields produce errors rather than invented values, and errors should be treated as genuine absence rather than retry opportunities.

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 with no filler. The core purpose is front-loaded, followed by concise validation and error-handling behavior. Every sentence earns its place.

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?

The description covers the main extraction flow and error semantics, and the output schema reduces the need to describe return values. However, it leaves the 'prompt' parameter undocumented and does not clarify URL handling or pagination, so an agent may not fully understand all inputs.

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 the description must compensate for all three parameters. It only loosely covers 'urls' and 'schema', but gives no detail about the 'prompt' parameter, its optionality, or how it affects extraction. This is partial compensation at best.

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 states a specific verb and resource: 'Extract structured data from one or more pages according to a JSON schema.' This clearly distinguishes it from sibling scraping/crawling tools by emphasizing schema-based structured extraction.

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?

The description implies usage through 'according to a JSON schema' and the error-handling note, but it does not explicitly state when to prefer this tool over siblings like scrape or crawl, nor does it list exclusions.

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