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

With zero annotations the description carries the full burden, and it delivers the expensive-to-discover facts: this is a paid call at $0.01, priced in USDC on Base (eip155:8453), settled via x402 with a payment object, and it returns per-URL verdicts plus a summary count. What it omits is failure semantics — whether one bad URL fails the whole batch or yields a per-URL error verdict — which matters for a batch preflight tool.

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 core purpose and the differentiation from /check, which is the right ordering. It loses a point for the near-duplicate cost statement ('$0.01/call' immediately followed by 'Price: $0.01 per call in USDC on Base...'), where the first fragment could be folded into the second without losing 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?

There is no output schema, so the description must cover returns, and it does state the shape (per-URL verdict plus summary count). Payment mechanics and the HTTP transport are covered too. The remaining gap is edge-case behavior for partial failures and over-limit input, which an agent calling a 20-item batch would want to know.

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% for the single 'urls' parameter, so the baseline would be 3, but the description adds real meaning beyond the schema: it supplies the payment envelope path params._meta["x402/payment"], which does not appear anywhere in the input schema. It does not add format nuance for the comma-separated string (scheme, trailing slashes, duplicates), so it is not a 5.

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 (preflight), a specific resource (up to 20 x402 endpoint URLs), and the batch scope in one clause. It also explicitly anchors itself to the sibling single-URL tool by saying each URL 'gets the same check as /check', so an agent can distinguish batch from x402check__check without opening either schema.

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?

'Cheapest way to vet a whole seller list' gives a clear use case and implicitly routes single-URL work to /check. It stops short of an explicit exclusion (e.g. 'do not use for one URL, use check instead') and does not say what to do when the list exceeds 20, so it is strong context rather than full routing guidance.

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