Skip to main content
Glama

AI Fusion One

Basic verification

basic_verification

Evidence report for a supplier (name and/or website) or a product (GTIN/UPC or name) from free public sources (Wikidata, DNS, HTTPS/TLS, RDAP, GLEIF incl. parents, GTIN check digit, Open Food/Products/Beauty Facts). For suppliers it also screens the name against OFAC/UK/UN sanctions lists (possible match - manual review; never a clearance), validates an EU VAT number via VIES (vat_number) and queries keyless registries for FR, NO, CZ, FI and PL (country, registry_id; PL needs the KRS number). Each check is verified, unverified or contradictory with source and timestamp. Not an authenticity or fraud guarantee. PAID tool: call without x402_payment to get the payment requirements. Price: $0.10 per call. Paid in REAL USDC on Base mainnet (chain 8453) via x402.

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": {
      "subject_type": "<subject_type>",
      "subject": "<subject>"
    },
    "name": "basic_verification"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
brandNo
trialNoFree trial instead of payment: a few calls per client per UTC day (shared across paid tools); result marked mode=trial.
countryNoSupplier country, ISO alpha-2 (e.g. DE, FR, NO, CZ, FI, PL).
subjectYesSupplier name, product name, or GTIN/UPC.
websiteNoClaimed public website/domain (no port or credentials).
vat_numberNoEU VAT number incl. prefix, e.g. DE811128135.
registry_idNoNational registry id (needs country): SIREN/SIRET FR, org no. NO, IČO CZ.
subject_typeYesWhat is being verified.
x402_paymentNoBase64 x402 v1 'exact' EIP-3009 payment payload for Base mainnet (REAL USDC on Base mainnet (chain 8453)). Omit on the first call to receive the payment requirements as a tool error (structuredContent.accepts); sign them and call again with this argument. One payment funds exactly one call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only carry generic hints (openWorldHint, non-idempotent, not destructive), but the description adds the traits an agent most needs: it is a paid tool at $0.10/call in real USDC on Base mainnet via x402, with the first call returning payment requirements. It also defines result semantics (each check is verified/unverified/contradictory with source and timestamp), scopes the sanctions screen as 'possible match – manual review; never a clearance', and disclaims authenticity/fraud guarantees.

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

Conciseness4/5

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

Purpose and sources are front-loaded, then caveats, then payment terms — a sensible ordering for a tool that will otherwise be mis-called. It is dense but each clause carries information; the only waste is the repetition of the USDC/chain 8453 payment detail that the x402_payment schema description already states.

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

Completeness4/5

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

For a 10-parameter, output-schema-less tool this is nearly complete: it explains the return shape (per-check status plus source and timestamp), the payment handshake, and the limits of the result. What is missing is peripheral — behavior when a subject or GTIN is not found, and any latency or rate-limit expectations beyond the trial the schema already documents.

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

Parameters4/5

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

Schema coverage is already 80%, so the baseline is 3, but the description adds real meaning beyond it: vat_number routes through VIES, registry_id is only useful with country and is supported for FR/NO/CZ/FI/PL with PL requiring the KRS number, and x402_payment funds exactly one call. The subject/subject_type pairing is stated naturally in prose rather than left purely to the enum.

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

Purpose4/5

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

The description opens with a specific verb+resource: an 'Evidence report' for a supplier (name/website) or product (GTIN/UPC/name), and enumerates the underlying sources (Wikidata, DNS, HTTPS/TLS, RDAP, GLEIF, GTIN check digit, Open Food/Products/Beauty Facts). An agent can tell this is a multi-source verification tool rather than a lookup or matching tool. It stops short of naming which sibling (basic_lookup, supplier_matching, web_check) to use instead, so it does not earn a 5.

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

Usage Guidelines3/5

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

Usage context is implied by the inputs (a supplier or product you need evidence on) and there is valuable procedural guidance — call without x402_payment first to receive requirements, PL requires the KRS number, registry_id needs country. However, no explicit when-to-use/when-not phrasing and no pointer to alternatives like basic_lookup or supplier_matching, leaving tool selection to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources