Skip to main content
Glama
YNAB MCP Server

YNAB MCP Server

search_transactions

Find YNAB transactions by payee, category, account, or date range, combining optional filters to narrow results and flag matching split-transaction portions.

Instructions

Searches transactions in a budget by payee, category, account, and/or date range. All filters are optional and combine together. The category filter also matches the portions of split transactions: a split that matches is returned as its parent transaction with the matching portions flagged "matched": true. Split transactions include a 'splits' array showing each portion's category and amount.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_transactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of results to return, most recent first.
budget_idNoThe budget ID, or 'last-used' for the most recently used budget.last-used
payee_nameNoPartial, case-insensitive match on payee name.
since_dateNoOnly include transactions on or after this date (YYYY-MM-DD).
until_dateNoOnly include transactions on or before this date (YYYY-MM-DD).
account_nameNoPartial, case-insensitive match on account name.
category_nameNoPartial, case-insensitive match on category name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.9.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations to lean on, the description does real work: it discloses split-transaction matching semantics, that a matching split is returned as its parent with portions flagged 'matched': true, and that splits appear in a 'splits' array. It omits result ordering beyond the schema's 'most recent first' and any notes on empty results or permissions.

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: capability first, filter-combination rule second, split-handling exception last. No filler, and the most surprising behavior (split flagging) is explained right where it matters.

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?

There is no output schema, so the description usefully covers the non-obvious part of the return shape ('splits' array, 'matched' flags) for split matches. It does not describe the shape of a normal transaction result, but with 100% schema coverage on the request side this is close to sufficient for a search tool.

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 coverage is 100%, so the baseline is 3; the schema already documents match type, date format, and defaults. The description adds one genuine semantic beyond the schema – that category_name also matches split portions – but leaves the other filters to the 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 opens with a specific verb and resource ('Searches transactions in a budget') and enumerates the four filter dimensions (payee, category, account, date range). This distinguishes it from singular-fetch siblings such as get_transaction, though it never explicitly names an alternative tool.

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?

'All filters are optional and combine together' explains how to use it, but not when to prefer it over get_transaction, largest_transactions, or list_uncategorized_transactions. Usage is implied by the filter list rather than stated as routing guidance.

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