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

Annotations only declare readOnlyHint and openWorldHint; the description adds real substance on top: the data source and refresh origin (0xB10C OFAC dataset, EVM list), the cost and payment rail ($0.005 USDC on Base via x402), and the concrete output verdicts (block/high_risk/caution/no_red_flags). It does not cover failure modes, latency, or what happens when an address is unknown, 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?

Front-loads the action and trigger, then stacks the check list, verdicts, and pricing in a dense but scannable sequence with no filler. The single long sentence-pile is slightly crammed, which costs it a point versus a cleanly segmented version.

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 carries the burden of explaining returns, and it does so by naming the verdict values and the individual signals inspected. It explains cost and data provenance, leaving only edge-case behavior (unknown address, upstream dataset outage) unspecified.

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, but the description adds meaning beyond the schema by explaining the mechanism of the optional 'expected' parameter (look-alike detection on matching first/last four hex characters). The 'address' parameter gains no extra semantics, but the one non-obvious parameter is clarified.

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+resource ('Wallet / counterparty screen') and enumerates exactly what is checked: OFAC SDN list, address type, tx counts, balances, burn detection, look-alike check. It also states the contract for the required parameter ('address to screen') and the verdict taxonomy, so an agent can distinguish it from siblings like base_token_check or x402_preflight without opening a 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?

Gives an explicit trigger condition ('before you send funds or accept a payer'), which is exactly the decision point an agent needs. It does not name competing tools or state when not to use it (e.g., for a plain token metadata lookup use base_token_check), so it stops short of full alternative routing.

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