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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive context beyond them — clutter removal, no browser needed, private-host refusal, pricing model, and that failed x402 or pack-credit calls are not charged. That failure/refund behavior is exactly the kind of operational detail an agent cannot infer from structured fields.

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 the core action and return shape, then moves to exclusions and pricing. The billing/refund sentences are long but arguably earn their place since the price is in the title and failure semantics affect invocation risk; still, they could be tightened.

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 fully compensates by naming the returned fields and the transformation applied. Input, exclusions, cost, and failure behavior are all covered — an agent has everything needed to call it correctly.

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 exists and the schema documents it at 100% coverage ('Public http(s) HTML page URL'), so the baseline would already be high. The description reinforces the constraint ('one public http(s) HTML page', non-HTML rejected), adding marginal value but nothing a schema reader couldn't infer.

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 ('readable text of a web page') and enumerates the return shape (markdown body, title, meta description, byline, excerpt). An agent can distinguish this from generic fetch or search siblings without reading the 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 positive contexts ('summarizing, quoting, or feeding a page to an LLM or RAG index') and explicit exclusions ('logged-in, paywalled or non-HTML URLs... private hosts are refused'). It stops short of routing to a specific sibling (e.g., url_probe or brief), so it earns a 4 rather than a 5.

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