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

With no annotations, the description carries the full burden and does well: it discloses the credit economics (300 credits to compile a recipe, 1 credit per row on replay) and the week-long negative caching of unreadable sites. It does not explain what the `js` flag changes or any auth/rate-limit behavior.

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?

Front-loads the core action, then the schema hint, then the cost/caching model in three tight paragraphs. The embedded code and line breaks are slightly noisy but every sentence carries information.

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?

An output schema exists, so return values need no explanation. An agent gets purpose, schema override, cost model, and caching caveat; only the `js` parameter remains a gap for a 4-parameter tool.

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%, so the description must compensate. It explains `fields` in useful detail (declaration syntax, default behavior) and `retry` explicitly, but `js` and `url` are left entirely undocumented.

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 ('Extract structured data') and scopes it emphatically to 'ONE page', which implicitly separates it from the sibling crawl_site. It never names an alternative tool outright, so the differentiation is inferable rather than explicit.

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?

Gives clear operational context: omit `fields` to fall back to the product schema, use `retry` to force a read of a site remembered as unreadable. It does not, however, say when to choose this over crawl_site or detect_site.

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