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

With no annotations, the description carries the full burden and does real work: it discloses the cost ($0.01 USDC on Base eip155:8453), the payment channel (x402 via params._meta["x402/payment"]), and the underlying HTTP endpoint. That is the crucial operational detail an agent needs before calling a paid tool. It stops short of describing rate limits, retry/refund behavior for failed URLs, or the return shape.

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 with the capability front-loaded, then pricing and payment mechanics. Every clause carries information; the only mild weakness is that the raw HTTP endpoint is buried in the same block as the payment terms rather than separated.

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 paid, 2-parameter tool with no annotations and no output schema, the payment and cost path is well covered, but the description never says what comes back (per-URL results? combined document? partial failure handling?) or whether a failed URL still costs a call. Those gaps matter more for a paid batch operation than for a free read.

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 50%: `urls` is documented and `format` has an enum but no prose explaining the difference between text, markdown, and json or which is default. The description does add one valuable non-schema detail — the hidden x402 payment field in params._meta — but says nothing about `format` semantics, leaving it at the baseline.

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 and resource with explicit scope: "Extract up to 10 pages in one paid call." The batching limit and the paid nature distinguish it from the single-page web_extract__extract sibling, though the description never names that alternative explicitly.

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 guidance is implied rather than stated: batching multiple URLs is the reason to choose this over a single-URL extract, and the 10-page ceiling plus per-call pricing hints at the tradeoff. There is no explicit when-to-use or when-not-to-use statement, and no named alternatives among the web_extract__* family.

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