extract_structured_data

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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety and open-web profile is covered. The description adds useful behavior beyond that by specifying exactly which page-level fields are extracted and by saying that canonicals pointing to another host are flagged. It still does not discuss fetch failures, redirects, or output formatting, but with annotations carrying the safety profile this is solid.

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?

The definition is a single dense sentence that leads with the verb and resource, then lists the extracted fields and the special cross-host canonical behavior. Every clause contributes to selecting or invoking the tool, with no filler or repetition.

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 one-parameter, read-only extraction tool, the description covers the target, the fields returned, and the special canonical flag, which compensates substantially for the absence of an output schema. It stops short of explaining return formats, size units, or failure behavior, which leaves some residual gap for an open-world fetch 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?

There is only one parameter, and its schema description is at 100% coverage with a concrete example URL. The description adds only the phrase "for a page," which does not materially extend meaning beyond the schema. The baseline 3 is appropriate because the schema already fully documents the parameter.

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 names a specific verb, "Extract," and enumerates the exact resource fields retrieved from a page: JSON-LD types, canonical, og:url, title, meta description, and initial-HTML text size. It also states a distinctive behavior, flagging cross-host canonicals. It does not explicitly differentiate itself from sibling tools such as check_ai_crawler_access or quick_readiness_report, which keeps it at 4 rather than 5.

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 implied by the action and target: an agent should use it when it needs those metadata fields from a page. However, the description gives no explicit when-to-use conditions, no exclusions, and no alternatives among the sibling check/report tools. That makes it minimally adequate rather than strong.

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