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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: fuzzy matching tolerates transliteration and spelling variants, dob and country re-rank but 'never hide a name match', the response contains the listed record, why it matched, and which lists were checked, and it discloses a 3-credit cost. That is exactly the behavioral context an agent needs before calling a screening service.

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 the action and coverage, then matching behavior, then exclusions, then cost — a sensible order with no filler sentences. It is dense and slightly run-on (multiple clauses separated by semicolons), but every sentence carries information.

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?

With no output schema, the description takes on the burden of describing returns ('the listed record, why it matched and which lists were checked') and does so. Combined with the stated list coverage, PEP exclusion, matching tolerance and cost, an agent has everything needed to call this correctly for a 7-parameter 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 the schema already documents all seven parameters including lists, minScore, limit and the IMO-number option for name. The description adds only the re-ranking semantics of dob and country and the fuzzy-name behavior; it says nothing about how minScore or lists interact with results, so it stays at the baseline.

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 and resource: 'Screen a person, company or ship by name' against four named sanctions regimes 'in one call'. The multi-list scope implicitly separates it from the single-regime siblings (ofac_check, uk_sanctions_check, eu_sanctions_check, un_sanctions_check), but it never names those siblings or the typed variants (sanctions_check_person/company/ship), so the differentiation is inferable rather than explicit.

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?

'Use for supplier, customer and payment screening' gives a concrete when-to-use context, and 'does not cover politically exposed persons (PEPs)' gives an explicit exclusion. It stops short of naming an alternative tool for PEP or for single-regime lookups, so the agent must infer routing to the per-list siblings.

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