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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses deterministic versioned rules, the x402 pay-per-call cost of $0.01 USDC, and the exact failure path (unpaid calls return payment requirements, then retry with X-PAYMENT or PAYMENT-SIGNATURE headers or params._meta["x402/payment"]). That auth/payment behavior is precisely the kind of context an agent needs before invoking a paid endpoint.

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-loaded with purpose, then output shape, then threat taxonomy, then payment mechanics — a sensible order with no filler. Slightly dense in the rule-hit enumeration and the header names, but every clause carries actionable information.

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?

Covers what the tool does, what it returns, its cost, and its failure/retry path, which is more than most definitions at this complexity. The remaining gap is input selection rules (url vs html vs text) and any size/timeout limits, which matters for a tool that fetches public pages.

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 the three inputs are already documented, and the description adds only that they are the accepted payload forms. It does not say whether the parameters are mutually exclusive, which one wins if several are supplied, URL reachability limits, or size caps — the main open semantic question for this tool.

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?

Opens with a concrete verb and input modes ("POST text, HTML or a public URL") and states a specific output (0-100 prompt-injection risk score with rule hits and character spans). It distinguishes itself from siblings such as pii_redact or html_to_rag by naming the exact threat classes it detects.

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?

Clearly frames the usage context (scan untrusted content for injection) and gives explicit retry mechanics for the payment flow. It does not, however, name when a caller should prefer pii_redact or url_to_markdown instead, nor does it explain how to choose among url/html/text.

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