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

No annotations are provided, so the description carries the full burden, and it does: rule-based methodology, evidence returned as what matched and where, explicit 'what was not checked' disclosure, signing and logging, and — critically — the exact payment negotiation protocol (call without payment yields an isError result with a 402 object in structuredContent; retry with the signed payment in _meta['x402/payment']). That is unusually rich behavioral disclosure for a paid tool with zero annotation coverage.

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 the value proposition and detection categories, then the evidence/trust properties, then the payment mechanics — a sensible ordering with no filler sentences. It is dense to the point of being a single wall of clauses, and the free-sample URL interrupts the flow, but every element carries information an agent needs.

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 two-parameter tool with no annotations and no output schema, the description covers the payment handshake, the signing guarantee, and the limits of its own analysis — the hard parts. The remaining gap is input contract detail (empty defaults, mutual exclusivity of url/text), which is the one thing an agent could get wrong on a first call.

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 0% — url and text have no descriptions at all — so the description must compensate. It does partially, mapping 'a text or public page' onto the two parameters, but it never states that both are optional with empty-string defaults, whether they are mutually exclusive, or which wins when both are supplied. An agent can guess the mapping but not the selection rule.

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 — determine whether text or a public page is attempting to steer the agent — and enumerates the concrete signal classes it detects (overrides, fake roles, exfiltration, tool abuse, payment requests, invisible Unicode, base64). This is clearly distinguishable from siblings like paid_citation_check, paid_mcp_audit, or verify_quote, which cover different verification domains.

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 a clear operational context ('before the agent reads it'), which tells an agent exactly where in a pipeline to place the call, plus a free sample endpoint to validate the shape first. It stops short of naming alternatives or stating exclusions (e.g., when a plain text heuristic is unnecessary), so it is clear context without explicit when-not guidance.

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