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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description adds genuinely new context: it costs one query against a Business plan allowance, returns a match grade, and warns that a similar name is not a confirmed match. It does not discuss rate limits or what an empty/failed response looks like beyond that caveat.

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 core check, then inputs, return shape, use case and cost — a logical order with little waste. The trailing bilingual keyword tag 'Sanctions screening (EU, UN, OFAC).' is redundant with the opening sentence and slightly dilutes the ending.

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 carries the return burden and does so: matches with grade, list, program, date, country and date of birth. Cost and plan gating are disclosed. The only residual gap — all three params are optional, so it never says at least one of cif/name is required — is minor.

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 baseline is 3; the description earns the extra point by clarifying that cif triggers checks on both the legal name and the current directors, and by framing cif and name as alternative input modes rather than combinable filters. It says nothing extra about the type enum (person/entity/any) that the schema doesn't already cover.

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: checks whether a Spanish company (by CIF, including its current directors) or a bare name appears on EU, UN and OFAC sanctions lists. The scope detail (three named lists, two input modes, director expansion) makes it unmistakable against siblings like verify_company or get_risk_profile.

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?

Explicitly names the moment to use it — client/supplier onboarding, KYB, anti-money-laundering — and separates the CIF path from the name path. It also flags the commercial precondition (Plan Business) and cost (1 query), which shapes invocation decisions. It stops short of naming a sibling alternative or stating when not to use it.

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