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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds materially: execution is parallel, the return values are enumerated (pass, review, block_review, incomplete), and payment/auth are spelled out (0.01 USDC via x402 or 5 API credits, first 5 paid calls daily free). Cost and payment mechanics are exactly the kind of behavior annotations cannot express.

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 trigger condition is front-loaded and every sentence carries payload: what is screened, what comes back, what it costs. The second sentence is a long run-on that packs three checks together, which costs a little readability but no information is wasted.

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 an 11-parameter, no-output-schema, paid tool this covers the essentials (verdicts, price, input flexibility) but omits how optional parameters change results, e.g. that kvk adds a bankruptcy check or how the pep flag behaves. An agent can call it, but cannot reason about which optional inputs to supply.

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 description coverage is only 45% across 11 parameters, so the description needs to compensate and largely does not. It names name, email, phone and vat, but says nothing about kvk (bankruptcy check), the pep toggle, type, company, country, birth_year or company_country, leaving most of the input surface undocumented in both places.

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 action with its full scope: sanctions screening against EU/UN/UK/US lists plus PEP, email and phone verification, and VIES VAT lookup, collapsed into one verdict. This clearly distinguishes it from the single-purpose siblings (eu_sanctions_screen, pep_screen, email_verify, phone_verify, eu_vat_check) as an aggregate check.

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?

"Use when onboarding a customer, seller or business and you want one answer" gives a concrete trigger, and "Send any of name, email, phone, vat" tells the agent the minimum input posture (no required params). It does not explicitly name the single-check siblings or say when to prefer them over this aggregate call, so no exclusion guidance.

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