Skip to main content
Glama

transfer_create

Initiate a SEPA transfer with beneficiary by ID or inline details. Handles SCA approval through polling or pending response for further processing.

Instructions

Create a SEPA transfer. Provide either beneficiary_id (existing beneficiary) or beneficiary (inline beneficiary object with name and iban), but not both. SCA: this operation may require Strong Customer Authentication; the tool polls inline by default (wait=30s) and falls back to a structured pending response so the caller can continue via sca_session_show + sca_session_token.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoOptional note
waitNoMaximum seconds (0-120) to poll inline for SCA approval before returning a structured pending response. Use false or 0 for a pure two-step flow (return immediately on SCA required). Default 30.
amountYesAmount to transfer
referenceYesTransfer reference
beneficiaryNoInline beneficiary object (mutually exclusive with beneficiary_id)
attachment_idsNoAttachment IDs (max 5, required for transfers > 30k EUR)
beneficiary_idNoExisting beneficiary UUID (mutually exclusive with beneficiary)
scheduled_dateNoScheduled date (YYYY-MM-DD)
bank_account_idYesBank account UUID to debit
vop_proof_tokenNoVoP proof token from verify-payee (auto-resolved when omitted)
sca_session_tokenNoSCA session token from a prior call to bind a previously approved SCA challenge to this retry. When set, no polling occurs and the operation runs exactly once with the token attached.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.1
  2. Removedv2.0.3
  3. Addedv2.0.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries full burden. It discloses SCA requirements, polling behavior (default wait=30s), fallback to pending response, and continuation via sca_session_show/sca_session_token. Could add error handling details.

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 with no fluff. First sentence covers purpose and key constraint, second covers SCA flow. Front-loaded and efficient.

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?

Covers main behavioral aspects and parameter nuances for a create tool with 11 parameters. Mentions pending response but lacks details on full success/error responses. Good for a tool with no output schema.

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%, baseline 3. Description adds value by explaining mutual exclusivity, wait parameter semantics, and sca_session_token usage. Goes beyond schema.

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 clearly states 'Create a SEPA transfer', specifying the verb and resource. It also clarifies mutual exclusivity of beneficiary parameters. However, it does not explicitly differentiate from sibling tool 'intl_transfer_create' for international transfers.

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?

Provides clear guidance on providing either beneficiary_id or beneficiary, and describes SCA handling with default polling and fallback. Lacks explicit when-to-use vs alternative transfer tools like intl_transfer_create.

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