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

With no annotations supplied, the description carries the full burden and does real work: it discloses that matching is fuzzy with numeric scores, that results carry programmes, aliases and DOB/nationality where available, that the call costs $0.05 USDC, and that output is a screening aid rather than a regulated AML/KYC determination. It still omits what a score threshold means in practice, how false positives surface, and any rate-limit or failure behaviour, so it stops 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?

The purpose and matching behaviour are correctly front-loaded in the first two sentences, but the tail collapses into pricing and upsell ('Batch: sanctions_batch $1. $0.05 USDC. Related: Full KYB pack... /uk-officer $0.15'), which is partly useful and partly redundant, and the batch alternative is stated twice in two formats.

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 screening tool with no annotations, no output schema and 0% schema coverage, the description covers what the tool queries and roughly what comes back, which is the essential half. It is nevertheless incomplete: three of five parameters are undocumented and the return shape is described only in a loose noun list, so an agent cannot confidently build a correct call for anything beyond the simple name-only case.

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 0% across five parameters, so the description must compensate and largely does not: 'type', 'year' and 'country' are never mentioned anywhere, leaving their meaning and expected format guesswork. The phrase 'DOB/nationality where present' reads as a description of returned record fields, not the input filters, so it does not even clearly document the 'dob' input.

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?

Opens with a specific verb (screen) and resource (a person or entity name), then enumerates the exact four list sources checked (OFAC SDN +non-SDN, UK FCDO, UN SC, EU). The sibling sanctions_batch is named explicitly, so an agent can separate the single-name tool from the batch tool without opening either schema.

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?

Gives a concrete worked example ({"name":"BANCO NACIONAL DE CUBA"}) and routes to the alternative for the 'many names' case with a stated threshold (<=50), which is real when-to-use guidance. It lacks any explicit when-not-to-use or stated preconditions for the fuzzy matching, and the routing names are duplicated in two different forms (sanctions_batch and /sanctions-batch), which muddies the handoff slightly.

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