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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, but the description goes far beyond. It discloses the automatic fallback from strict to fuzzy, the scoring mechanism (Jaro-Winkler, phonetic), the label 'approximate' with raw scores, pagination behavior (totalAvailable, hasMore, nextOffset), and the critical caveat that an empty result does not mean 'cleared'. This is substantial behavioral context that an agent needs to interpret results correctly, and it does not contradict the annotations.

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 longer than minimal but deliberately packed with necessary detail. It is front-loaded with the core purpose and immediately states the output. Each sentence contributes: mode mechanics, pagination, and the essential compliance caveat. No fluff, and the structure progresses logically from function to modes to pagination to disclaimer.

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?

Given the complexity (7 parameters, two modes, pagination, scoring), the description covers all critical aspects: input types, source restrictions, entity type filtering, score floors, match mode behavior, pagination instructions, and result interpretation. An output schema exists to describe return structure, so the description does not need to repeat that. An agent has enough information to call this tool correctly and understand its results, including the important 'not cleared' caveat.

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% (all parameters described in JSON Schema), so the baseline is 3. The description adds meaningful semantics: it explains the strict mode's exact-normalized and all-tokens-present logic, the fuzzy mode's scoring and approximation labeling, the behavior of minScore (fuzzy only), and the pagination semantics of offset/nextOffset. These details enhance understanding beyond the raw schema definitions.

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 and resource: 'Screen a name (person, company, vessel, aircraft) against all loaded sanctions watchlists at once.' It names the exact lists (OFAC SDN + Consolidated, EU, UK, UN) and the output (scored potential matches). This clearly differentiates it from the sibling tools, which focus on getting designations, entities, sources, resolving, or tracing ownership.

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 explains when to use this tool: for screening names across multiple watchlists with fuzzy and strict matching, and it provides context on the strict/fuzzy modes and automatic fallback. It also gives important guidance on interpretation ('screening AID', not a compliance determination). It does not explicitly name alternative sibling tools but the context of screening is distinct from the getter/resolver siblings, making usage clear enough.

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