Wise MCP Server

Close a currency balance

close_balance

Destructive

Close a Wise balance or Jar after removing funds; Wise refuses closure while it holds money, and a person must approve the action.

Instructions

Close a balance or Jar. Wise refuses while it holds money. A person approves it.

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": {
      "id": "<id>"
    },
    "name": "close_balance"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The balance id, from list_balances.
`confirm`	No	Set true only when the user asked for exactly this action.
`profile`	No	The Wise profile id to act for. Defaults to WISE_PROFILE_ID, else the only business profile. See list_profiles.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Nov 7, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds two things the annotations cannot: a server-side refusal condition (non-empty balance) and an approval requirement, both of which change how an agent should prepare the call.

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, front-loaded with the action, then the failure condition, then the approval gate. No redundant restatement of the title and nothing that could be cut.

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 destructive, non-idempotent mutation with no output schema, the description covers the two things an agent most needs: the precondition that blocks success and the human-approval requirement. It does not say what remains after closure or what the response contains, which keeps it from a 5.

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 already carries a description, including the defaulting rule for profile and the usage constraint on confirm. The description adds no parameter-level detail beyond loosely motivating confirm via the approval sentence, so the baseline 3 applies.

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?

States a specific verb (close) and resource (balance or Jar), which cleanly separates it from the open_balance sibling. It stops short of naming that sibling or spelling out the full scope of what 'close' removes, so a 4 rather than a 5.

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?

The clause 'Wise refuses while it holds money' is a genuine precondition that tells an agent when the call will fail, and 'A person approves it' signals a human-confirmation step. However, there is no explicit routing to alternatives (e.g. emptying the balance first) or statement of when not to attempt the call.

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