Skip to main content
Glama

IoMarkets.tech ISO 20022 Test Bench

Reconcile a bank statement

reconcile_statement
Read-only

Match an ISO 20022 bank statement (camt.053.001.08) or notification (camt.054.001.08) against the payments you expected (open invoices, a payment run, a ledger export) and list the exceptions: amount mismatches (short or over payments, charges taken), entries on the statement nobody expected, and expected items not on it. Matches by reference (EndToEndId, InstrId, TxId, AcctSvcrRef, UETR, creditor reference), by remittance text, one payment for several invoices when they add up exactly, and by amount within a date window; each match says why. Exact decimal arithmetic. Nothing is stored. Same code as https://iomarkets.tech/reconcile. Pass sample: true to run the built-in demo.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "reconcile_statement"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoHow many days apart the expected date and the booking date may be for a match on amount alone (default 3).
sampleNoIgnore statement and expected and reconcile the built-in sample (a made-up EUR account) to see how it works.
expectedNoWhat was expected: CSV text with a header row, or a list of objects. Columns: reference, amount (required), currency (default: the statement's), direction (credit/debit or in/out; without it a negative amount is a debit), date (YYYY-MM-DD), counterparty. Up to 5000 rows.
statementNoThe camt.053 or camt.054 XML.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds real substance beyond them: exact decimal arithmetic, nothing is stored, each match reports its rationale, the matching strategies used, and a sample mode. It omits operational detail such as the response size for large statements or how ambiguity between multiple candidate matches is resolved, keeping it below 5.

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?

Front-loads the core action and keeps a dense, information-rich structure with no filler sentences. The enumeration of six reference types (EndToEndId, InstrId, TxId, AcctSvcrRef, UETR, creditor reference) and the external URL are borderline padding for an agent deciding how to call it, costing a point.

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 complex, multi-input tool with no output schema, the description does describe what comes back (a list of exceptions with reasons) and covers all four inputs plus a demo path. It stops short of specifying the response shape or how to interpret multiple competing matches, which an agent would still have to discover at call time.

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 the schema already documents days, sample, expected and statement, making 3 the baseline. The description adds only modest meaning on top — that days governs amount-only matching within a date window and that one payment can settle several invoices when they add up exactly — but it does not explain accepted reference formats or the currency fallback beyond what the schema states.

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?

Names a specific verb and resource pair: match a camt.053/camt.054 statement against expected payments and list exceptions. It further enumerates the three exception classes (amount mismatches, unexpected statement entries, missing expected items), which lets an agent distinguish it from validate_message or explain_issue without opening any schema.

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?

Gives clear usage context: reconciliation of a statement against open invoices, a payment run, or a ledger export, plus an explicit demo mode via sample: true. It does not state when NOT to use it (e.g. use validate_message for schema validation instead) or name a sibling alternative, so it falls short of a 5.

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