OFAC SDN Screening

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

With no annotations provided, the description carries the full burden. It discloses that the tool takes no input, returns no PII, includes hash values, and clarifies an important subtlety about the staleness flag keying on fetch age rather than publish age. It does not explicitly state that it is read-only, but 'Return' plus 'No input' strongly implies it.

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 with no filler. The primary action and resource are front-loaded, the return fields are enumerated compactly, and the key behavioral nuance about fetch age vs publish age 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 zero-parameter metadata tool without an output schema, the description fully covers what is returned, the staleness threshold, the version-confirmation use case, and the no-input/no-PII safety property. Nothing essential is missing.

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 tool has zero parameters and the input schema fully reflects that. The description reinforces this with 'No input, no PII,' which is helpful. Since there are no parameters to document, the baseline of 4 applies.

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 states a specific verb ('Return') and resource ('provenance AND freshness of the loaded OFAC SDN list'), then enumerates the exact data returned. It is clearly differentiated from the sibling screen_sdn, which performs screening rather than metadata inspection.

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 the intended use: 'Use this to confirm which list version a screening ran against, and how current it is.' It does not explicitly say when not to use it or name screen_sdn as the alternative, but the use case is clear enough given the sibling context.

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 provided, the description carries the full burden of behavioral disclosure, and it succeeds. It reveals that the query is not stored or anchored, that the data is a dated snapshot, that matches are informational rather than legal determinations, and that human review is required. It also previews the output shape by mentioning ranked matches, list entries, and matched fields.

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 three focused sentences: purpose, output contract, and essential caveats. Every sentence earns its place, and the most decision-relevant information is front-loaded.

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?

The description explains the return verdicts and match details even though no output schema exists, and it communicates the key caveats around persistence and compliance. Minor operational details, such as error behavior or how to learn the snapshot date via the sibling tool, are not covered, but the core invocation needs are met.

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?

All four parameters are already fully documented in the input schema with 100% coverage, so the baseline of 3 applies. The description adds only indirect context about how narrowing parameters might influence results, but it does not repeat or enhance per-parameter semantics.

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 concrete verb and resource: 'Screen a name against a dated snapshot of the public OFAC SDN list.' It specifies the three possible verdicts and the ranked-match output, making the tool's function unmistakable and clearly distinct from the sibling metadata tool get_sdn_list_meta.

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 clearly establishes the intended use case — screening names against the OFAC SDN snapshot — and adds important context about when results should not be treated as final ('requires human review'). It does not explicitly name alternatives or list when-not-to-use conditions, but the screening context is unmistakable.

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