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 discloses the output verdict tiers (ok/caution/block with plain reasons), the per-call price and payment rail ($0.02 USDC on Base via x402), and a liability disclaimer ("rules-based, not legal advice"). It stops short of stating that the call is read-only and sends no transaction, which is exactly the reassurance an agent needs before invoking a payment-adjacent 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 decision question, then the check inventory, then return values, then cost. The comma-delimited check list is dense but each item is a distinct capability the agent may need to justify the call. No filler sentences.

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 4-parameter tool with no output schema and no annotations, the description supplies what an agent needs to call it correctly: coverage per chain, what the token parameter triggers, the shape of the returned verdict ('each check in full'), and the pre-call payment cost. Nothing material is omitted beyond the read-only reassurance noted above.

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 earns a bump by clarifying that Solana coverage is narrower ("wallet kind and activity on Solana" versus first funder and large transfers on the five EVM chains) and that supplying a token adds a 0-100 score. It never mentions the `expect` parameter, whose mismatch-behavior is left entirely 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 plain-language question that states the exact decision it supports, then enumerates the concrete checks performed (OFAC SDN, wallet age, EOA vs contract, first funder, large transfers, token risk score). The composite framing implicitly separates it from single-purpose siblings such as address_sanctions_screen, token_risk_check and the per-chain wallet_profile tools.

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?

"One check before sending or accepting crypto" gives a clear triggering context and the chain list scopes where it applies. It does not explicitly route the agent to alternatives: prepayment_safety_check_lite (cheaper subset), address_sanctions_screen (sanctions only) or token_risk_check (token only) are never named, so the agent must infer when the full check is worth $0.02 versus a narrower one.

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