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

The annotations already declare readOnlyHint, destructiveHint false, openWorldHint true and idempotentHint false, so the bar is lower. However, the description adds real value: it discloses the price ($0.009/call), the free tier, that failed calls are free, and the reason repeats are not free, which directly explains the idempotentHint=false annotation. The 'screening aid, not legal advice' caveat is also useful context about the response's authority.

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 verb and resource, then usage triggers, then the caveat and pricing, all in one dense block with zero filler sentences. Nothing is repeated and every clause carries information an agent needs before calling.

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 compensates by describing the verdict values and match payload (SDN id, programs), which is exactly what an agent needs to interpret results. It leaves open how partial name matches are ranked and whether the verdict thresholds are configurable, but for a two-optional-parameter screening tool this is close to complete.

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 100%, so both parameters are already documented, including that every word of a name must appear in a listed name or alias. The description adds only an example address value and restates that address, name or both may be supplied, which is baseline value at best.

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 concrete verb and resource: screens an address or a person or company name against the OFAC SDN list, and even names the return shape (verdict of block/review/pass plus matches, SDN ids, programs). It does not differentiate itself from the close sibling sanctions_check, so an agent still has to guess which of the two to call.

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 three concrete trigger situations: before paying or accepting funds, when onboarding a counterparty, and as the compliance step of an agent payment flow. It stops short of explicit when-not guidance or naming the sibling tools (check_counterparty, check_payee, sanctions_check) as the alternatives, which is what would push this to a 5.

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