Skip to main content
Glama
bunq Banking MCP

bunq Banking MCP

review_financial_records

Read-onlyIdempotent

Audit supplied payment records locally with exact decimal math and conservative transfer checks; requires each payment's monetary account and ID, without fetching history or inferring taxes.

Instructions

Review supplied records locally with exact decimals and conservative transfers.

Every payment needs monetary_account_id and id. This tool fetches no history,
proves no source completeness, makes no tax or active-subscription inference,
and never adds card attempts or invoice totals to settled Payment cash totals.

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": {
      "payments": "<payments>",
      "own_accounts": "<own_accounts>"
    },
    "name": "review_financial_records"
  }
}

Input Schema

NameRequiredDescriptionDefault
invoicesNo
paymentsYes
card_actionsNo
own_accountsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.5

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive), yet the description adds real behavioral context beyond them: it does no network history fetch, makes no source-completeness proof, makes no tax or active-subscription inference, and explicitly refuses to fold card attempts or invoice totals into settled Payment cash totals. Those exclusions matter for interpreting results. It still says nothing about the response shape or any limits on input size.

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?

The core capability and its local/exact-decimal character are front-loaded, and the negative clauses are compact. The list of exclusions is dense but each item is distinct and earns its place. Slightly better structuring (grouping the exclusions or separating input constraints from behavior) would push it higher.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotation about return values, the description needed to explain what a "review" yields, and it does not. Combined with the unexplained invoices, card_actions, and own_accounts inputs, an agent can call the tool but cannot predict or interpret its output. The negative-capability statements are helpful but insufficient for a four-parameter financial tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameter burden, and it only partly does. It states that every payment requires monetary_account_id and id — useful constraints that live inside the payments objects rather than the top-level schema — but invoices, card_actions, and own_accounts are never explained at all. Three of four top-level parameters remain undefined.

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 names a concrete verb and resource ("Review supplied records") and adds qualifying traits: local execution, exact decimals, conservative transfer handling. It implicitly separates itself from read_account_history by stating "This tool fetches no history," so an agent can tell it apart from the sibling. What remains unclear is what a "review" produces, so it stops short of 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?

Usage is only implied: the tool operates on records the caller already holds, since it "fetches no history." That tells the agent not to use it for retrieval, but it never names an alternative (e.g., read_account_history) or states the condition that should route to it. Adequate but leaves the when-to-use decision to inference.

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