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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive); the description adds substantial behavior beyond that: data is a mirrored copy with an as-of date, matching tolerates case/accents/typos/transliterations/company suffixes/place words, results are ranked with scores and alias attribution, the same party appears once per list, and a no-match outcome is possible at the chosen threshold. These are exactly the traits an agent needs to interpret results and set expectations about staleness and recall.

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?

Purpose is front-loaded and every clause carries information about scope, matching tolerance, or output, with no filler. The main structural weakness is that the bulk is one very long compound sentence, which makes it slower to scan than a short paragraph with separate lines for scope and return values.

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 and seven parameters, the description carries the full burden and does so: it spells out the return payload (score, matched alias, list, programs, type, addresses, countries, IDs, official link, as-of date) and the no-match case. Combined with full schema coverage and clear safety annotations, an agent has everything needed to call it and interpret results.

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, and the description earns above that by explaining the consequences behind parameters: what the threshold means for match strength, that filtering can drop and count entries, and that per-list duplication is expected. It stops short of restating detail/limit/type semantics, which is acceptable since the schema already documents them well.

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 and resource ("Screens one person, company, vessel or aircraft name") and enumerates the exact datasets searched, so the agent knows precisely what the tool does. The word "one" implicitly distinguishes it from the plural sibling screen_parties, but that contrast is never made explicit, leaving a small ambiguity for an agent choosing between the two.

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?

Usage context is implied rather than stated: the description explains defaults (all loaded lists, threshold 0.85) and points to list_status for checking which mirrors are loaded, which is genuine routing help. However, it never says when to prefer screen_party over screen_parties, when to lower min_score, or what a no-match at threshold should prompt next, so the agent must infer the decision rules.

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