Screen names against official sanctions lists

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: it discloses that the call runs the Apify Actor tacps126/sanctions-screener on the user's own Apify account, that cost is roughly $0.003 per name with a hard $0.5 cap per call, that matching applies transliteration and name-normalisation rules, and that output is a verdict plus matched entries. The account-dependency and spend cap are exactly the operational facts an agent needs before calling.

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 scope and covered lists are front-loaded, followed by matching behaviour, output shape, disclaimer, and finally cost/account mechanics — a sensible order with no filler sentences. Despite being a dense paragraph, every clause carries information an agent would otherwise have to guess.

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 7-parameter tool with a nested object and an output schema, the description covers everything material: data sources, matching logic, result semantics, cost model, spend cap, and account prerequisite. Return-value detail is somewhat redundant given the output schema, but that is a minor surplus rather than a gap.

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 100%, so the baseline is 3; the description earns a bump by decoding the opaque `lists` enum values into publisher names (e.g. 'us-ofac-cons' → OFAC consolidated non-SDN, 'ch' → Switzerland SECO). It also explains the fuzzy-matching behaviour that `min_score` controls (transliteration, word order, patronymics, initials, company forms), though it does not directly discuss `country`, `date_of_birth`, or `extra_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?

States a specific verb and resource ('Screens people and organisations against the official sanctions lists') and enumerates the exact publishers covered (OFAC SDN/consolidated, UN, EU, UK, Canada, SECO). No sibling tool does anything comparable, so the tool is unambiguously identifiable from the name and first sentence alone.

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 clear usage context (compliance/AML screening of persons and entities) and adds the important caveat 'A screening aid, not legal advice,' which frames when the output should and should not be relied on. It does not explicitly state exclusions or name an alternative tool, but no sanctions-related sibling exists to route away from.

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