Verify a business partner in one call: EU VAT registration (VIES), LEI register (GLEIF), IBAN checksum and country consistency — one verdict (pass|fail|inconclusive) with an auditable check log. Provide at least one of name, vatId, lei. Does not include commercial-register existence checks. 150 credits, requires an API key.
| Name | Required | Description | Default |
|---|---|---|---|
| lei | No | ||
| iban | No | ||
| name | No | ||
| vatId | No | ||
| country | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It importantly discloses cost (150 credits), the API key requirement, the composite verdict/check-log return, and the exclusion of commercial-register checks. This is strong for a non-annotated tool, though it does not elaborate on error handling or what makes a result 'inconclusive'.
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 two dense sentences that front-load the core purpose and efficiently pack in the checks, output format, input requirements, exclusions, and cost/auth prerequisites. Every phrase earns its place with no redundancy or filler.
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 a multi-source verification tool with no output schema, the description covers the return contract (verdict + check log), input preconditions, exclusions, and pricing/auth. It could go further in documenting parameter semantics and explicit alternatives, but overall it provides sufficient context for an agent to decide on and invoke the tool.
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 0%, so the description must compensate. It clarifies that name, vatId, and lei are the identifier alternatives, and it hints at iban's role via 'IBAN checksum and country consistency'. However, it leaves the 'country' parameter and its relationship to IBAN ambiguous, and does not state whether iban/country are optional or required in certain combinations.
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 clearly states the action ('Verify a business partner'), enumerates the underlying checks (EU VAT via VIES, LEI via GLEIF, IBAN checksum/country consistency), and specifies the output format ('one verdict (pass|fail|inconclusive) with an auditable check log'). This specific verb+resource+scope combination distinguishes it from sibling single-purpose validators like validate_vatid and validate_iban.
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 provides an explicit input precondition ('Provide at least one of name, vatId, lei') and a clear exclusion ('Does not include commercial-register existence checks'). While it does not explicitly name alternative tools, the 'one call' phrasing and combination of checks clearly imply when it should be used instead of individual validators.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly distinct, but validate_vatid and validate_vatid_format could be confused at a glance, and verify_company overlaps with validate_iban and validate_vatid in scope. However, detailed descriptions and explicit mentions of differences help an agent choose correctly.
All tools follow a consistent verb_noun pattern with lowercase and underscores: screen_sanctions, validate_email, validate_iban, validate_vatid, validate_vatid_format, verify_company. The verb varies but the structure is uniform.
Six tools is a well-scoped number for a validation API covering sanctions, email, IBAN, VAT, and a combined company verification. Each tool serves a clear purpose, and the count feels neither sparse nor bloated.
The set covers core validation areas (sanctions, email, IBAN, VAT, company verification) but intentionally excludes PEP screening and commercial-register checks, as noted in the descriptions. These minor gaps do not prevent core workflows, though they limit full KYC coverage.