OFAC SDN Screening

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

With no annotations, the description carries the full burden. It discloses that the tool takes no input, returns provenance details, and has no PII, which implies a safe read-only operation. It could explicitly state that it does not modify any data, but the metadata-focused nature and 'No input' make the behavior sufficiently clear.

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?

Two sentences, zero filler. The first sentence immediately states the returned fields, the second adds the version-confirmation use case. Every word earns its place.

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?

For a tool with no parameters, no output schema, and a simple provenance-returning function, the description covers purpose, return values, usage context, and safety characteristics. Nothing essential is missing for an agent to select and invoke it 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?

There are zero parameters, so the schema already covers everything. The description adds the meaningful clarification that the tool accepts 'No input,' which directly prevents an agent from looking for arguments. This meets the baseline for no-parameter tools.

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 'Return' and names the resource 'provenance of the loaded OFAC SDN list,' then enumerates the exact outputs: source URL, publish date, record count, fetch time, and content hashes. This clearly distinguishes it from the sibling tool 'screen_sdn' by focusing on metadata rather than screening logic.

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?

Explicitly states 'No input, no PII' to set expectations, and provides a concrete use case: 'Use this to confirm which list version a screening ran against.' This signals when to use this tool (version confirmation) and implicitly contrasts with screen_sdn for actual screening, giving clear guidance.

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

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

With no annotations, the description fully carries the behavioral transparency burden. It discloses that queries are not stored or anchored on this path, and that a potential match is informational and requires human review, not a legal or compliance determination. These are critical behavioral traits that go beyond the schema and help calibrate agent expectations.

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 extremely concise, consisting of two sentences. It front-loads the core purpose, then provides return value details and important caveats without unnecessary fluff. Every sentence earns its place.

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?

Given the tool's moderate complexity (4 params, all documented) and lack of output schema, the description adequately explains the return behavior (verdict, ranked matches, matched field) and adds context about statelessness and the need for human review. It could mention potential pagination or result limits, but these are likely not critical for a screening tool.

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 all four parameters are already documented with clear descriptions. The tool description adds no additional parameter-specific context beyond what the schema provides, so the baseline of 3 is 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 clearly states the tool's function with a specific verb+resource: "Screen a name against the public OFAC SDN list." It also describes the output (verdict and ranked matches) and distinguishes it from the sibling metadata tool by focusing on screening rather than list metadata.

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 implies when to use this tool (for screening against OFAC) and provides an important usage note about human review for potential matches. It does not explicitly mention the sibling tool or exclusion scenarios, but the purpose is clear enough that an agent could infer appropriate usage.

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