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

Annotations only say readOnly/openWorld=false; the description adds substantial context beyond them: results come from a cache with no new endpoint request, ranking inputs (observed unpaid availability, 402 shape, price consistency, Lint risk), that missing evidence stays unknown, and that scores are not safety or proof of paid delivery. The payment-failure and unknown-outcome handling rules are exactly the kind of behavioral disclosure an agent needs and cannot infer.

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 pricing are front-loaded and the 'How to pay (MCP)' section gives readable structure. However, the 'Illustrative output excerpt' and its 'not a live result / signature / approval or guarantee' boilerplate appear twice, and the stacked Never/Only-after hedges add bulk without new 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?

For a paid, stateful-looking read tool with no output schema and 0% param coverage, the description does cover pricing, payment handshake, failure handling and a sample response shape. It is still incomplete on two of four parameters and never states what the ranked result fields actually contain beyond the empty-results excerpt.

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 0%, so the description carries the full burden, yet only 'capability' and 'limit' get any treatment (example input plus 'up to 12' free-vs-paid framing). The 'network' and 'max_price_usd' parameters are never explained, leaving half the inputs with no semantics anywhere.

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 sentence 'Search cached public x402 sellers by capability' states a specific verb, resource and scope, and 'cached public' implicitly separates it from the check_* / lint_* siblings that probe live endpoints. It stops short of naming an alternative tool, so a 5 is not warranted.

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 conditions: first three matches free, extended results cost 0.01 USDC, no shared trial, and a generic MCP connector without payment support cannot complete a paid continuation. It also prescribes the STOP / inspect accepts / obtain approval / retry with _meta['x402/payment'] flow. What it lacks is guidance on when to choose this index versus check_endpoint, check_listing or lint_endpoint.

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