Wise MCP Server

Check bank details against a recipient

check_bank_details

Read-onlyIdempotent

Compare a payment request or invoice's payee name and bank details against a saved recipient, field by field, before paying; stop and verify any differences.

Instructions

Compare the name and bank details in a payment request or invoice with a saved recipient, field by field, and say which match and which differ. Run it before setting up a payment from an invoice: any difference means stop and confirm with the payee another way, never update the recipient from the invoice. Only reads; account numbers come back masked to their last four characters.

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": {
      "recipient_id": "<recipient_id>"
    },
    "name": "check_bank_details"
  }
}

Input Schema

Name	Required	Description
`name`	No	The payee's name as the request gives it.
`details`	No	The bank details as the request gives them, such as {"iban":"DE89 3704 0044 0532 0130 00"}.
`recipient_id`	Yes	The saved recipient, from find_recipient.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Nov 7, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered; the description still adds real value by disclosing that results are per-field match/differ and that account numbers are returned masked to the last four characters. It does not describe what happens when the recipient is missing or the details are malformed, which keeps it short of a 5.

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 tight sentences: what it does first, when to run it and what to do with the outcome second, the read-only/masking caveat last. No repetition of the title and no filler.

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?

With no output schema, the description carries the burden of describing the return, and it does explain that the response reports which fields match and which differ and that account numbers are masked. It stops short of specifying the result shape (e.g., per-field statuses vs. a single verdict) or failure behavior, which would make it fully self-sufficient.

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% and every parameter (name, details, recipient_id) is documented there, including an example for the nested details object. The description only implies the comparison semantics without adding format, casing, or normalization rules for the name/details fields, so it meets but does not exceed the baseline.

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: compare name and bank details from a request/invoice against a saved recipient, field by field, reporting matches and differences. This clearly distinguishes it from sibling read tools like get_recipient (fetch a record) or find_recipient (look one up), since it performs a comparison rather than a retrieval.

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

Usage Guidelines5/5

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

Gives an explicit trigger ('Run it before setting up a payment from an invoice') and an explicit rule for handling the result ('any difference means stop and confirm with the payee another way, never update the recipient from the invoice'). The only minor gap is that it doesn't name sibling alternatives, but the schema already points recipient_id at find_recipient.

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