Skip to main content
Glama

Bank payment QR payload

qr_payload_payment
Read-onlyIdempotent

Build a bank payment payload: a Pix BR Code (Brazil), a SEPA credit transfer (EPC069-12, euro area), or a PayNow (Singapore), PromptPay (Thailand) or VietQR (Vietnam) code, EMV merchant-presented with its CRC. Fields depend on the scheme. Pass the result as data to generate_qr_code; use error correction M for SEPA.

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": {
      "scheme": "<scheme>"
    },
    "name": "qr_payload_payment"
  }
}

Input Schema

NameRequiredDescriptionDefault
bicNosepa: BIC, optional inside the EEA
cityNopix: receiver city, up to 15 characters
ibanNosepa: IBAN
nameNopix: receiver name (required, up to 25 characters); sepa: beneficiary name (required); paynow: name shown to the payer
txidNopix: transaction ID, up to 25 letters and digits
proxyNopaynow or promptpay: the mobile number, UEN, national/tax ID or e-wallet ID
amountNoAmount in the scheme's currency (BRL, EUR, SGD, THB, or whole VND). Leave out to let the payer choose.
expiryNopaynow: last day the code works, YYYY-MM-DD
pixKeyNopix: CPF, CNPJ, +55 phone, email or random key
schemeYespix (Brazil), sepa (euro credit transfer, EPC069-12), paynow (Singapore), promptpay (Thailand) or vietqr (Vietnam)
bankBinNovietqr: the bank's 6-digit BIN
messageNopix or vietqr: message for the payer
editableNopaynow: whether the payer may change the amount (default true)
proxyTypeNopaynow: mobile or uen; promptpay: mobile, id or ewallet
referenceNosepa: structured RF creditor reference; paynow: bill reference
remittanceNosepa: payment reference text, up to 140 characters (not with reference)
accountTypeNovietqr: account (default) or card
accountNumberNovietqr: account or card number

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

The annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. Beyond that, the description adds real behavioral content: output is an EMV payload including a computed CRC, fields are scheme-dependent, the amount can be omitted so the payer chooses, and the result feeds generate_qr_code with error correction M for SEPA. It omits what happens when a scheme-required field is missing, but the added context is substantial.

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?

Two sentences, both earning their place: the first front-loads the verb, the resource, and the scheme enumeration with regions for disambiguation; the second gives the downstream handoff and the one non-obvious encoding detail. No filler or restatement of the title alone.

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 an 18-parameter, scheme-conditional builder with no output schema, the description supplies what matters: that the result is a payload string to be consumed by generate_qr_code, and that only scheme-relevant fields apply. The remaining gap is that it does not say whether irrelevant or unknown fields are ignored or rejected, which an agent calling with mixed scheme params would want to know.

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 100%, so the baseline would be 3, and the description goes above it by stating the cross-cutting rule that 'fields depend on the scheme' — a conditional constraint an agent would otherwise have to reconstruct from 18 per-field scheme prefixes. It also clarifies amount semantics (scheme currency, nullable to let the payer choose), which reframes the schema's 'Leave out to let the payer choose' as an intentional behavior.

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?

The description leads with a specific verb and resource ('Build a bank payment payload') and then enumerates exactly which schemes are covered (Pix BR Code, SEPA EPC069-12, PayNow, PromptPay, VietQR, EMV/CRC). The closing instruction to pass the result as `data` to generate_qr_code separates it cleanly from that sibling without any schema inspection.

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?

It states the workflow context clearly: use this to construct the payload, then hand off to generate_qr_code, and use error correction M for SEPA. It also signals that field requirements vary by scheme. It stops short of explicit when-not-to-use guidance (e.g. versus the email/SMS/vCard payload siblings), so it is clear context rather than a full 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.