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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the safety bar is already met. The description adds genuinely new information beyond that: SSRF guarding, that the full body is deliberately omitted, and a concrete cost of $0.001 per call — all useful for invocation decisions.

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 dense sentences that front-load the extracted fields and then append constraints and cost. No filler, every clause carries information the agent needs.

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?

No output schema exists, but the description enumerates the returned fields, so the agent knows the shape of the result. Security posture and cost are both disclosed, leaving nothing essential unstated for a single-parameter read 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?

With a single parameter at 100% schema coverage, the schema already documents the URL and its http(s) pattern. The description's 'public HTTP(S) page' phrasing mirrors the schema constraint rather than adding format or syntax detail, so the baseline of 3 applies.

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 (Extract) and resource (web page metadata) and enumerates exactly which fields are returned (title, description, OG image/site name, author, date, canonical URL, language). The clause 'does not return the full body' implicitly separates it from the sibling extract_webpage_markdown, so an agent can pick between the two without opening either 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?

Gives clear conditions: a public HTTP(S) page, no full body returned, SSRF-guarded. The exclusion of full-body content implies when to prefer extract_webpage_markdown, but that sibling is never named, so the routing guidance stops short of explicit alternatives.

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