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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral facts: SSRF guarding (internal targets are rejected), that the full body is NOT returned (bounding response size/expectations), and a per-call price of $0.01. It does not say how missing or malformed metadata is handled, but the disclosure exceeds the annotation baseline.

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 short sentences, front-loaded with the returned fields (the most decision-relevant information), followed by the SSRF/no-body constraint and the cost. Nothing is redundant and no sentence could be dropped without losing a fact.

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?

With no output schema, the description correctly compensates by enumerating the returned metadata fields, and it pairs that with the SSRF guard and pricing. Remaining gaps are modest: no statement about behavior when fields are absent, redirects, or non-HTML content types, which matter for a single-URL 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?

Only one parameter with 100% schema description coverage (format uri, pattern ^https?://, 'Public HTTP(S) page URL.'), so the schema already carries the semantics and a baseline 3 applies. The description's mention of 'public' reinforces the SSRF-relevant restriction but adds no syntax, normalization, or redirect-following detail beyond the schema.

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 concrete verb and resource (extract metadata) and enumerates the exact fields returned — title, description, OG image/site name, author, publication date, canonical URL, language — plus the constraint to public HTTP(S) pages. It stops short of distinguishing itself from the sibling extract_webpage_markdown, which also operates on a web page URL, so an agent must infer that this one returns structured fields rather than body text.

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 phrase 'public HTTP(S) page' implicitly excludes internal/authenticated URLs, and the stated $0.01 cost supports a cost/benefit decision before calling. However, there is no explicit 'use this when you need fields X instead of the full content' routing against extract_webpage_markdown, which is the obvious near-neighbor in the sibling list.

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