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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: fuzzy word-order-independent matching, returned fields (scores, list, program, aliases), a 12-hour list refresh cadence, a legal-disclaimer, and the x402 payment behavior ($0.009 USDC on Base/Solana/Polygon/Arbitrum).

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 action and covered lists, then capabilities, then a caveat, then params, then pricing. Dense but nearly every clause carries decision-relevant information; the pricing/sample sentences are long but justified for an agent that must handle payment.

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?

No output schema exists, and the description compensates by naming the return fields (scores, list, program, aliases) and the refresh cadence. Combined with complete param documentation and the payment/disclaimer context, an agent has enough to invoke it correctly; only the precise threshold semantics are unstated.

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 description coverage is 0%, so the description carries the full parameter burden and largely does so: it names all four params, marks name as required and type as optional, gives the enum values for type, the 0.5–1 range and 0.85 default for threshold, and the default 10 for limit. It does not explain what the threshold value semantically means (similarity cutoff), leaving a minor gap.

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 (screen) and resource (person or company name) and names the three exact data sources (OFAC SDN, EU consolidated, UN Security Council). This distinguishes it from nearby siblings like kyb_check, scam_message_check, and company_lookup without opening any 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?

Usage is implied by the description ('screen a person or company name') and the caveat 'a screening aid, not a legal determination' frames the output's limits, but there is no explicit when-to-use vs when-not, and no alternative sibling (e.g., kyb_check) is named for adjacent compliance needs.

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