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

Beyond the readOnly/idempotent/destructive annotations, the description discloses failure behaviors: unavailable sources appear in sources_unavailable, reason_code becomes 'partial_screening' and never 'clear', and screening_status must be branched on instead of matched because matched:false is also false when nothing could be screened. It also states the tool never fabricates a match or clear. These are critical edge-case disclosures the annotations cannot convey.

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?

Long but effectively partitioned into labeled blocks: core description, example queries, WHEN TO USE, WHEN NOT TO USE, cost, and latency. The critical UN-list caveat is front-loaded, and no section is purely filler. It could be tightened by moving cost/latency and some examples out, but overall it is appropriately structured for a complex compliance tool.

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?

There is no output schema, so the description carries the full burden of explaining the return contract. It defines screening_status values, the relationship between matched and screening_status, match fields (score, program, source URL), lists_screened, sources_unavailable, and reason_code semantics. It also covers usage contexts, exclusions, cost, and latency — an agent has enough to select, invoke, 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?

Schema description coverage is 100%, and the schema already explains name, type, and country in detail — including that country annotates/ranks and never removes results. The description adds example query-to-parameter mappings, but no new parameter semantics beyond what the schema provides. Baseline 3 is therefore appropriate.

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 opens with a specific verb phrase — 'Free screening of a name or entity against official sanctions lists' — and enumerates the exact lists screened (OFAC SDN, EU consolidated, UK FCDO). It explicitly excludes the UN list, which distinguishes it from generic sanctions-check tools. This is a clear, resource-and-scope-specific purpose statement.

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?

WHEN TO USE names concrete trigger scenarios: pre-onboarding, payments, vendor engagement, due diligence. WHEN NOT TO USE excludes full KYC/AML screening, PEP databases, adverse media, credit risk, and bulk screening, and clarifies that a negative result is informational only. This gives an agent explicit routing criteria and alternatives.

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