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

Goes well beyond the annotations: discloses fuzzy matching behaviour, the exact response shape (per-name possible-match flag, top score, up to 3 scored matches with their lists), the 25-name cap, and a complete cost model (0.0012 USDC/name, 0.03 USDC or 15 credits, first 5 paid calls free). For a paid tool, pricing and payment prerequisites are the key behavioural facts and they are all here.

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?

Three sentences, front-loaded with the trigger and scope before pricing details. Every sentence carries information, though the two pricing sentences partially overlap (per-name cost vs. total cost vs. free-tier).

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 no annotations describing returns, the description fully specifies what comes back per name and how matches are scored. Batch limits, payment options, and the free tier are all covered, which is everything an agent needs to invoke this paid tool correctly.

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 50%: the 'names' parameter is already documented with the ';' separator and example, and the description only reinforces the 25-name cap. The 'type' enum (person/entity) has no description in either the schema or the description, so an agent gets no guidance on when to set it.

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 (screening), resource (names of people/companies) and precise scope: up to 25 per call against four named sanctions lists. The batch scope distinguishes it from the single-record eu_sanctions_screen sibling, even though that sibling is not named.

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?

Opens with an explicit trigger ('Use when screening a list of people or companies at once') and names concrete use cases (customer bases, payouts, vendor lists). It stops short of naming the single-name alternative eu_sanctions_screen for one-off checks, so the boundary is implied rather than stated.

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