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

Annotations already declare read-only, open-world, non-destructive, but the description goes well beyond them: 200KB HTML and 8s caps, private targets blocked, 422 on no match, the billing policy (uncharged errors on Base, other rails may charge), the $0.015 x402/USDC-on-Base price, and a warning that returned content is untrusted third-party data. These are exactly the operational facts 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?

The purpose and return shape are front-loaded in the first two sentences, with limits, errors, pricing, and trust caveats following in priority order. It is dense but nearly every clause is load-bearing for an agent. The one cost is a run-on final stretch cramming pricing, payment rail, and legal terms into a single breath.

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?

There is no output schema, so the description must describe return values itself — and it does, listing title, description, canonical, language, links, images, headings, jsonLd, textSample, plus per-field values and fieldErrors. Combined with caps, blocking rules, error codes, and billing behavior, an agent has everything needed to call this 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?

Schema description coverage is 100%, so the schema already documents url, html, fields, the selector/attr/all/limit sub-shape, the max-20 limit, and the fieldErrors behavior. The description restates the same facts (GET url vs POST body, max 20 fields) without adding syntax or edge-case guidance the schema lacks. Baseline 3 applies when the schema carries the parameter burden.

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?

The opening clause names the operation and resource precisely: a scraping API that turns a public page or supplied HTML into JSON fields, and it enumerates the default return shape. An agent immediately knows this is structured extraction rather than a raw fetch. It stops short of a 5 because it never explicitly contrasts itself with siblings like fetch, http, or pdf, which overlap in the 'retrieve a web resource' space.

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?

It gives concrete invocation routing: use GET with a url, or POST with JSON {url or html, fields}, and explains that supplying fields yields matched values plus fieldErrors. That is actionable context for choosing between the two call shapes. There is no explicit when-not-to-use clause or pointer to an alternative sibling, so it falls short of the top band.

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