Skip to main content
Glama
ISO 20022 Payment Evidence & Investigation MCP

ISO 20022 Payment Evidence & Investigation MCP

investigate_payment

Correlate pacs.008 with pacs.002 and report bank-reported reasons with exact provenance, uncertainty, and human-approved next steps. Read-only. Requires two supplied XML messages; no external banking connectivity.

Instructions

Correlate pacs.008 with pacs.002 and report bank-reported reasons with exact provenance, uncertainty, and human-approved next steps. Read-only. Requires two supplied XML messages; no external banking connectivity.

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": {
      "pacs008_xml": "<pacs008_xml>",
      "pacs002_xml": "<pacs002_xml>"
    },
    "name": "investigate_payment"
  }
}

Input Schema

NameRequiredDescriptionDefault
pacs002_xmlYes
pacs008_xmlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose 'Read-only' and 'no external banking connectivity', which are meaningful behavioral facts an agent could not otherwise know. It stops short of stating whether analysis is deterministic, whether it can be called repeatedly without side effects, or how large inputs are handled, so meaningful gaps remain for a no-annotation tool.

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?

Three short sentences with zero filler. The capability statement comes first, followed by the safety trait and the input constraint, which is exactly the right priority order.

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 two-parameter, no-output-schema tool, the description effectively doubles as a return-value summary by naming what is reported (bank reasons, provenance, uncertainty, suggested next steps). Only edge-case behavior, such as unresolved correlations or malformed XML, is left unaddressed.

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 coverage is 0%, so the description must compensate: it does confirm both parameters exist, are required, and are raw XML messages, and the correlation framing implies pacs.008 is the original payment and pacs.002 the status report. It adds no guidance on encoding, size limits, or whether well-formed-but-unmatched messages are accepted, so the compensation is only partial.

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?

States a specific verb and resource ('Correlate pacs.008 with pacs.002') plus a concrete output object ('bank-reported reasons with exact provenance, uncertainty, and human-approved next steps'). No sibling (parse_message, validate_message, explain_message, lookup_code, generate_test_message) correlates two messages and reports reasons, so the distinction is clear from the definition itself.

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?

Implies the use case (investigating why a payment was rejected or returned) and states a prerequisite that both XML messages must be supplied. However, it never says when to use validate_message or parse_message instead, nor what to do if only one message is available, leaving routing to inference.

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