Assess x402 services (paid)

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

The description goes beyond annotations (which don't indicate paid or two-call behavior) to disclose the full payment flow: call without signature to get challenge, sign accepts[0], retry with signature; it explains probe pricing, non-refundable fees, no charge if fresh run cannot be produced, and that probe responses are truncated and never verbatim. It also warns to read amount from accepts[0].amount. No contradictions with annotations.

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 description is dense and thorough, front-loading the core purpose and payment flow. It earns its length by covering substantive caveats (pricing, refund, probe truncation). A slight deduction because the description is very long and repeats the $0.25 fee and 'never charged for nothing' concepts in a slightly redundant way, but every sentence adds important security or usage detail.

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?

The description is complete: it explains the required two-call protocol, how to compute the correct amount, what happens with probes, fee consequences, error/refund behavior, and the report contains probe_report. Given there is no output schema, the description fully compensates by describing what is returned (report, probe_report, verdict, truncated extracts) and what is never returned (verbatim body).

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?

The schema already covers all 4 parameters with high coverage, and the description adds critical semantic meaning for the key 'payment_signature_b64' parameter (omit on first call, set on retry), the 'probe' object's behavior (pricing, ignored when not armed), and the 'services' array (1-8, found via siblings). It explains the exact relationship between parameters and the two-call flow.

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 description clearly states the tool performs a paid assessment of service slugs against a user's need, and explicitly distinguishes it from sibling tools search (find services) and get (read cached assessment). It specifies a paid action with a $0.25 USDC fee and a two-call challenge/response flow.

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?

The description explicitly tells the agent when to call this tool: when free signals are exhausted and choosing wrong costs more than a quarter, and it contrasts with x402_search_services and x402_find_best_service, and references x402_get_service for already-computed assessments, giving clear alternatives and conditions.

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