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

Beyond the readOnly/destructive annotations, it discloses why the UN list is excluded, that lists_screened reflects only lists that actually ran, that failed sources appear in sources_unavailable, and that reason_code is 'partial_screening' if any source is unavailable. It also warns never to fabricate a match or clear and instructs the agent to branch on screening_status rather than matched.

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?

The description is well-structured with clear sections and front-loads the core purpose before caveats and examples. It is longer than strictly necessary, with four similar example queries, but the length is largely purposeful given the multiple sanctions lists, failure modes, and disclaimers that need explicit handling.

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 takes on the burden of explaining return values and does so thoroughly: screening_status enum, matched, match details, lists_screened, sources_unavailable, reason_code, and partial-screening behavior. It also covers cost, latency, and use-case boundaries, giving an agent everything needed to call and interpret the tool correctly.

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?

The input schema already documents all three parameters with 100% coverage, so the description does not need to compensate. The example queries add illustrative mappings from natural language to parameters, but the substantive semantics, such as country annotating/ranking without removing results, come from the schema itself. Thus the description adds only marginal parameter-level value.

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?

The description names a specific verb ('screening'), a specific resource (a name/entity against official sanctions lists), and enumerates exactly which lists are included (OFAC, EU, UK) and which is not (UN). This clearly distinguishes it from siblings like lookup_us_contracts and verify_company_record.

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?

Dedicated WHEN TO USE and WHEN NOT TO USE sections give explicit trigger conditions (onboarding, payment, vendor engagement, due diligence) and explicit exclusions (not KYC/AML, not PEP/adverse media/credit risk, not bulk screening). It also names alternative screening domains and provides cost and latency considerations.

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