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

Annotations cover safety (readOnly, idempotent, non-destructive, openWorld), so the description adds metering and cost behavior: a shared 100 calls/day free bucket across all web tools, then 1 credit per call over x402 with no API key. That is genuinely useful operational context. It omits failure behavior (what happens on non-HTML or blocked pages) and whether 'cached' implies staleness, keeping it below 5.

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 purpose, then labeled When-to-use / Do-not-use / Returns / Metering blocks. Dense but every line carries distinct information an agent needs; no filler sentences.

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 single-parameter read tool, the description covers purpose, routing, the full return shape (compensating for the absent output schema), and metering constraints. Nothing material to correct invocation is missing.

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 schema coverage is 100%, with the schema itself documenting the http(s) URL and 2048-char limit. The description adds no further parameter guidance, so baseline 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 (page's structured metadata), then enumerates exactly the field families returned (OG, Twitter cards, canonical, language, JSON-LD). It is clearly distinguishable from web_fetch and web_screenshot by the explicit do-not-use routing.

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 a concrete when-to-use condition ('you need title/description/author/image ... or JSON-LD for a product/article, without reading the whole page') and explicit exclusions pointing to named siblings web_fetch and web_screenshot for text and screenshots respectively.

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