Skip to main content
Glama

kyb_findings

Read-only

Screen a company for KYB risk by checking sanctions, PEP, offshore-leak, regulatory, beneficial-owner, adverse-media, and company-register records; use it to vet partners before onboarding.

Instructions

Screen a company for KYB risk: sanctions and PEP matches, offshore-leak records, regulatory records, beneficial owners and adverse media, plus the company register's answer (registry_match, good standing). Structured findings, each naming the kind of source; no AI-written summary.

    Use this for "screen / vet / check X for sanctions, PEP or bad
    press". For only "does it exist / is it active", company_lookup is
    far cheaper. Usually 30-90 s (the tool waits for queued results).

    Price: EUR 0.50 per call, charged even when nothing is found (a new
    account's first call is free). Rate limit: 10 calls a minute per key.

    Args:
        company_name: Legal name of the company (e.g. "Tesco PLC")
        website: Company website URL (http/https), strongly recommended:
            it separates the company from others with a similar name
        country: ISO 3166-1 alpha-2 country of registration. Without it
            no company register is searched (registry_match NOT_SEARCHED)
        registration_number: The register's company number; needs country
        state: US only: 2-letter state of formation
        vat_number: VAT number with its country prefix, e.g. "DE123456789"
    

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "company_name": "<company_name>"
    },
    "name": "kyb_findings"
  }
}

Input Schema

NameRequiredDescriptionDefault
stateNo
countryNo
websiteNo
vat_numberNo
company_nameYes
registration_numberNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.3.0
    • addedInput schema / properties / country
      Added value: +{
      +  "default": "",
      +  "title": "Country",
      +  "type": "string"
      +}
    • addedInput schema / properties / registration_number
      Added value: +{
      +  "default": "",
      +  "title": "Registration Number",
      +  "type": "string"
      +}
    • addedInput schema / properties / state
      Added value: +{
      +  "default": "",
      +  "title": "State",
      +  "type": "string"
      +}
    • addedInput schema / properties / vat_number
      Added value: +{
      +  "default": "",
      +  "title": "Vat Number",
      +  "type": "string"
      +}
  2. First observed

TDQS

A5/5.0
Behavior5/5

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

Annotations only cover the safety profile (readOnly/openWorld/not destructive); the description adds the costly details an agent actually needs: EUR 0.50 charged even on empty results, first call free, 10 calls/minute rate limit, blocking 30-90 s wait, and structured findings with no AI summary. It also discloses a hidden behavioral consequence of omitting country (registry_match becomes NOT_SEARCHED).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then routing, then cost/latency, then parameters — a sensible order for an agent deciding whether to call. The Args block is dense but every line adds constraint or format information absent from the schema, so nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, slow, open-world screening tool the description covers purpose, alternatives, cost, rate limits, latency, and the gating effect of country. Return shape is partly described (structured findings naming source kinds, no AI summary) and an output schema exists, so no further return-value detail is required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does: each of the six parameters is explained with an example and a rationale (website disambiguates similar names, country gates register search, registration_number requires country, state is US-only, vat_number needs its country prefix). This is meaning well beyond bare property names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Screen a company for KYB risk") and enumerates the exact source classes covered (sanctions, PEP, offshore leaks, regulatory records, beneficial owners, adverse media, registry match/good standing). It also distinguishes the scope from the cheaper existence-check sibling, so an agent can pick it without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit use-case trigger ("screen / vet / check X for sanctions, PEP or bad press") and an explicit exclusion routing to company_lookup for "does it exist / is it active". It even sets expectations on runtime (30-90 s, waits for queued results), which affects how an agent should sequence calls.

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