sanctions_screen

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

With no annotations, the description carries the full burden and does well: it discloses cost ($0.009 USDC per call), latency (p99 8000ms), list refresh cadence (every 12 hours), fuzzy/word-order-independent matching behavior, and a scope disclaimer. It omits auth requirements and explicit rate limits, keeping it short of 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-loaded with purpose and sources, then matching behavior, refresh, disclaimer, params, and finally cost/latency. Dense but every sentence carries operational information; no filler.

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, so the description correctly names the return fields (scores, list, program, aliases). Combined with cost, latency, and refresh disclosure, an agent has enough to call it correctly; error behavior and auth expectations are the remaining gaps.

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 0%, so the description must compensate, and it does: it documents name (required), type with both enum values, threshold range (0.5–1, default 0.85), and limit (default 10). Only minor bounds (limit max 25, min 1) are left to the schema.

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+resource ('Screen a person or company name against the official OFAC SDN list... EU consolidated... UN Security Council consolidated list') and names the exact data sources. An agent can distinguish it from siblings like kyb_check or company_lookup purely from this text.

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?

The description establishes the screening context and adds an important caveat ('A screening aid, not a legal determination'), which implies it should not be used as a compliance verdict. However, it never says when to prefer this over adjacent siblings (kyb_check, domain_compliance) or that a name match must still be adjudicated elsewhere — usage is implied rather than explicit.

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