code402

Counterparty Risk Indicators

pre_disbursement_guard

Read-onlyIdempotent

Check supplier tax and bank identifiers (IBAN, LEI, EU VAT, UK company number), domain-age evidence and country mismatch signals before vendor payment. Requires a preceding receipt hash. An advisory result is not verified identity, fraud clearance or authorization to release funds.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "vendor_domain": "billing@acme-consulting.co.uk",
      "company_number": "01234567",
      "recipient_iban": "GB82WEST12345698765432",
      "declared_country": "GB",
      "prev_receipt_hash": "0x0000000000000000000000000000000000000000000000000000000000000000",
      "invoice_amount_usd": 4500
    },
    "name": "pre_disbursement_guard"
  }
}

Input Schema

Name	Required	Description
`lei`	No	ISO 17442 Legal Entity Identifier (optional).
`vat_number`	No	EU VAT number (optional).
`vendor_domain`	No	Vendor website domain or invoicing email address (optional).
`company_number`	No	Official corporate registration number, e.g. UK Companies House 8 digits/chars (optional).
`recipient_iban`	No	Recipient bank IBAN (optional).
`declared_country`	No	2-letter ISO country code where vendor claims to be registered (optional, e.g. 'GB', 'US', 'DE').
`physical_address`	No	Vendor physical office address (optional).
`prev_receipt_hash`	No	Preceding verification receipt hash (may also be passed via X-PREV-RECEIPT-HASH header).
`invoice_amount_usd`	No	Disbursement transaction amount in USD (optional).

Output Schema

Name	Required	Description	Default
`tool`	No
`scope`	No
`checks`	No
`summary`	No
`decision`	Yes
`risk_level`	Yes
`risk_score`	Yes
`flags_triggered`	No
`recommendations`	No
`clear_to_disburse`	Yes
`inspected_counterparty`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 17, 2026
RemovedOct 15, 2026

Changed2 schema fields changedOct 15, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "company_number": "01234567",
-    "declared_country": "GB",
-    "invoice_amount_usd": 4500,
-    "recipient_iban": "GB82WEST12345698765432",
-    "vendor_domain": "billing@acme-consulting.co.uk"
-  }
-]New value: +[
+  {
+    "company_number": "01234567",
+    "declared_country": "GB",
+    "invoice_amount_usd": 4500,
+    "prev_receipt_hash": "0x0000000000000000000000000000000000000000000000000000000000000000",
+    "recipient_iban": "GB82WEST12345698765432",
+    "vendor_domain": "billing@acme-consulting.co.uk"
+  }
+]

addedInput schema / properties / prev_receipt_hash

Added value: +{
+  "description": "Preceding verification receipt hash (may also be passed via X-PREV-RECEIPT-HASH header).",
+  "type": "string"
+}

AddedSep 25, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Beyond the readOnly/idempotent hints, it discloses two things annotations cannot: the receipt-hash prerequisite and that the result is advisory — not verified identity, fraud clearance or release authorization. That is genuine expectation-setting about output trust level.

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?

Three tight sentences with the scope, the prerequisite and the disclaimer, and the resource checked is front-loaded. No filler, though the identifier list could be compressed.

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

Completeness3/5

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

Output schema and annotations are rich, and the advisory disclaimer is helpful. But the description says a receipt hash is required while the schema declares zero required parameters, leaving the agent unsure what minimum input actually produces a useful result.

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

Parameters3/5

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

Schema description coverage is 100%, so all nine parameters are already documented; the description only restates the identifier families at a high level. It adds no format, precedence or minimum-input guidance.

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?

States a specific verb+resource: it checks a named set of counterparty identifiers (IBAN, LEI, EU VAT, UK company number), domain-age evidence and country mismatch in a pre-payment context. That composite scope is distinguishable from single-identifier siblings like iban_check or lei_check, though no sibling is named explicitly.

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

Usage Guidelines4/5

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

'before vendor payment' plus 'Requires a preceding receipt hash' gives a clear trigger and prerequisite. It does not say when to prefer the individual validators (iban_check, lei_check, vat_mod97_check) over this composite guard, so exclusion guidance is absent.

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

All code402 tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.