Skip to main content
Glama
Life Admin MCP

Life Admin MCP

by NKC27

Import bank statement

import_bank_file

Read a bank CSV export and add its transactions to your spending records, sorted by category, with a preview before saving. Already-imported lines are skipped, so overlapping statements are safe.

Instructions

Read a bank statement exported as CSV (every UK bank app can export one) and add its transactions to the person's spending records, sorted into categories. Always run first with confirm false to show a preview, then again with confirm true once the person agrees. Already-imported lines are skipped, so overlapping statements are safe. The file stays on this computer.

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": {
      "path": "<path>"
    },
    "name": "import_bank_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesFull path to the .csv file, e.g. ~/Downloads/statement.csv
confirmNofalse (default) previews; true saves

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare the generic write profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false, idempotentHint=false), so the description usefully adds that duplicate lines are skipped, that the source file is read locally and not uploaded, and that the write only lands on the second, confirmed call. There is a mild tension between "already-imported lines are skipped, so overlapping statements are safe" and idempotentHint=false, but the dedupe claim is about overlapping file content rather than repeated identical calls, so it is not a direct contradiction. It still doesn't cover failure modes (malformed CSV, missing columns) or what permissions the local file needs.

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?

Four short sentences, front-loaded with what the tool does, then the required call sequence, then the safety guarantees. Every sentence carries distinct information with no repetition or 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?

For a two-parameter write tool with full annotation coverage and no output schema, the description covers the essentials: purpose, mandatory preview-then-confirm flow, duplicate handling, and data locality. The remaining gap is error behaviour on unreadable or wrongly formatted statements, which matters for a file-path-based tool but is secondary.

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 both parameters are already documented, and the description goes beyond that by spelling out the two-step semantics of confirm (false = preview, true = save) and by framing path as a bank-exported CSV file. It adds operational meaning rather than restating the schema, though it gives no format or encoding constraints beyond "CSV".

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?

"Read a bank statement exported as CSV ... and add its transactions to the person's spending records, sorted into categories" gives a concrete verb (read/import), a concrete resource (CSV bank statement), and the downstream effect (categorised spending records). That is enough for an agent to separate this bulk-import tool from single-entry siblings such as add_spending or categorise without opening the schema.

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?

The description states the usage protocol explicitly and in order: always preview with confirm false first, then re-run with confirm true once the person agrees, and it notes overlapping statements are safe to import. It does not say when *not* to reach for this tool or name an alternative (e.g. manual add_spending for a handful of entries), which keeps it short of a 5.

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