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

Beyond the annotations (openWorldHint=true, destructiveHint=false), the description discloses the two facts an agent most needs: the call costs $0.01 per URL and is paid via x402 Exact through params._meta['x402/payment']. This also explains why readOnlyHint=false for what is otherwise a read-style check — the charge is the side effect — and the verdict vocabulary plus the do-not-pay rule define the decision behavior after the call.

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 action and its timing, then the return contract, then the trigger list, then the cost — a sensible order with no filler sentences. The "Use when:" list is dense with near-duplicate phrasings ("is this API a scam" vs "is this endpoint safe or legit"), which adds recall value but is slightly repetitive.

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?

With no output schema, the description correctly carries the return shape (verdict enum plus the three history fields), and it covers cost, payment mechanics, and the post-call decision rule. Gaps remain around failure modes — what happens for a non-x402 or unreachable URL, and cache TTL behind the fresh flag — but these are secondary for a single-URL preflight.

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 both url and fresh are already documented and the baseline is 3. The description earns above that by documenting a payment parameter that does not appear in the schema at all (params._meta['x402/payment']) and by tying the per-URL charge to the url argument, which matters for cost accounting.

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?

"Preflight an x402 seller URL before settle / PAYMENT-SIGNATURE" names a specific verb (preflight), a specific resource (x402 seller URL), and the moment of use in the payment flow. The return contract (verdict ok|caution|avoid plus uptime, payToChanges, priceChanges) further pins the scope, and "that tool's history only" signals this is a single-endpoint check rather than an aggregate or deep audit.

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?

An explicit "Use when:" list covers six concrete triggers (about to pay, is this a scam, debugging a 402, checking uptime, validating requirements before signing USDC), plus a decision rule: "Do not pay if verdict=avoid." What is missing is routing guidance against siblings — nothing says when to prefer deep_check, preflight_batch, or verify_payto over this single-URL call.

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