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

With no annotations, the description carries the full burden and does substantial work: it names the verdict vocabulary (stop/check/ok), discloses the folded-in payee check with DO_NOT_PAY mapped to stop and CAUTION/unreadable mapped to check, and explains the paid x402 handshake including price ($0.001, USDC on Arc/Base/Solana or XNT on X1). It does not describe the response payload shape or latency, and never explicitly states this is a non-mutating lookup, which keeps it below a 5.

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?

Information-dense but written as long run-on fragments, and several sentences describe the operator's own internal payouts (the X reward, jury pay, the hunter bounty, buy-and-rate) that an external caller cannot act on. The critical instruction — the payment two-step — is buried at the very end rather than front-loaded.

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 pre-send safety check this covers the essentials: what it returns conceptually, what causes each verdict, cost and payment mechanics, and failure behavior. Missing return-field detail is partially excused by the enumerated verdict values, but an agent still does not know the full response structure or whether verdicts are cached.

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 the baseline is 3; the description adds real meaning beyond it by explaining the payment parameter's two-step protocol (call without `payment` to get terms, sign with your own wallet, call again with `payment`) and by framing `from` as "the sender really used" — i.e. the history used for lookalike detection. `token` and `to` semantics are left to the schema.

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?

Opens with a specific verb-like framing ("Send guard for Arc: call before sending USDC or a token") and enumerates exactly what it screens for: address poisoning lookalikes, forged-transfer bait, token contracts/burn addresses, OFAC SDN and USDC blacklist, fake USDC/EURC, brand-new addresses. It also separates itself from the related sibling by stating that the signed verdict lives in arc_payee_check, not here.

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 an explicit trigger ("call before sending USDC or a token") and clarifies an edge case agents will worry about: a first payment to a new address is still allowed, and a failed read is refused before payment. It does not explicitly route to alternatives (e.g. when arc_counterparty or arc_trust_check would be preferable), so it stops short of full when/when-not guidance.

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