extract

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

Goes beyond the readOnlyHint/openWorldHint annotations by disclosing the two-stage implementation (markdown scrape then AI sampling), which signals added latency and non-determinism, and by claiming bot-detection/CAPTCHA bypass. No contradiction with annotations, but cost/rate-limit behavior is unstated.

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 front-loaded sentences, dominant purpose stated first, with implementation and reach details following. Tight overall, though the CAPTCHA sentence leans promotional rather than operational.

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?

For a two-parameter, read-only, open-world scraping tool with no output schema, the description covers what it does, how it does it, and how reliable it is. Return shape is inherently dynamic, so its omission is acceptable.

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 50%: extraction_prompt is documented in-schema while url is not. The description mentions scraping a webpage, which makes url self-evident, but adds nothing about extraction_prompt behavior beyond what the schema already says. Baseline 3 fits at this coverage level.

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?

States a specific verb+resource ('scrape a webpage and extract structured data as JSON') and implicitly occupies a distinct niche from siblings like scrape_as_markdown and scrape_as_html. An agent can tell what it returns (JSON, not markdown/HTML) without opening the schema.

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?

Usage is only implied: extract JSON when structured data is needed, versus scrape_as_markdown for raw text. No explicit when-to-use, when-not-to-use, or named alternative (e.g. 'use scrape_as_markdown if you don't need structure') is given, leaving routing to inference.

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