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

Far exceeds the annotations: it discloses the paid/402 mechanism, that unreadable pages are not charged, that failures after settlement are not charged, that everything unproducible returns >=400 uncharged, that requests pass through an SSRF guard, and that the JS is not executed. These are exactly the behavioral facts an agent needs beyond readOnlyHint/openWorldHint/idempotentHint.

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 pricing/payment constraint is front-loaded and the audit scope is delivered as a dense but scannable enumeration. It is long, but nearly every clause carries distinct information (checks, severity output, payment flow, SSRF).

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, single-input audit tool this covers everything: what is fetched, what is measured, the return shape (issues with severity, raw measurements, 0-100 score), and the full payment lifecycle. An output schema exists, so the description needn't detail return values, yet its brief mention adds clarity rather than redundancy.

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 100%, so baseline is 3, but the description adds genuine payment semantics: payment is forwarded as the PAYMENT-SIGNATURE header and never as body data, the first call should omit it, and nothing is charged for the 402 itself. That contextualizes the 'payment' parameter beyond the schema text.

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 ('Audit one public web page') and precisely scopes what is examined: served HTML without JS, plus /robots.txt and sitemap. The enumerated check list and the sibling set (web_read, site_contacts, domain_intel) make it easy to distinguish this from other page-oriented tools.

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?

Clear context for when to use it (technical SEO/crawler-view audit of a single public page) and an explicit operational flow: omit payment on the first call, pay via the returned 402 template, or let the fiatdock-mcp package handle it. It does not explicitly name an alternative sibling to use instead for adjacent needs (e.g. web_read for raw content), so it stops short of full when-not guidance.

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