Skip to main content
Glama
pragprogrammer

YNAB MCP Server

update_transactions

Update multiple transactions at once for bulk recategorization, approval, or clearing. Each transaction is identified by ID or import_id and only provided fields are updated.

Instructions

Update multiple transactions in a single API call.

Each transaction must include either 'id' or 'import_id' for lookup (not both). Only provided fields are updated (sparse update). Ideal for bulk recategorization, bulk approval, bulk clearing, etc. Updating subtransactions on an existing split is not supported. Future-dated transactions are not permitted.

Args: plan_id: The plan ID (use list_plans to find available IDs) transactions: List of transaction dicts. Each must include EITHER: - id: The transaction ID OR - import_id: The transaction's import_id (used for lookup, cannot be changed) And optionally any of: - account_id: New account ID - date: New date (YYYY-MM-DD) - amount: New amount in dollars (negative for outflow, positive for inflow) - payee_id: New payee ID - payee_name: New payee name - category_id: New category ID (use null with subtransactions to create a split) - memo: New memo (max 500 chars) - cleared: 'cleared', 'uncleared', or 'reconciled' - approved: Whether the transaction is approved - flag_color: 'red', 'orange', 'yellow', 'green', 'blue', 'purple', or null - subtransactions: For creating a new split, list of dicts with: amount, payee_id, payee_name, category_id, memo exclude_fields: Optional list of field names to exclude from each updated transaction. If omitted, the model's default exclude list is used (see FIELDS.md). Pass [] to return all fields. Pass a custom list to override the default.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
plan_idYes
transactionsYes
exclude_fieldsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

No annotations provided, so the description carries full burden. It discloses behavioral traits: sparse update, lookup options, unsupported features. It does not detail error handling or idempotency, but overall provides sufficient transparency.

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 description is fairly long but well-structured with a summary, bullet points, and detailed Args. It is front-loaded with purpose. Slightly verbose due to extensive parameter docs, but necessary given schema coverage.

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 an output schema present, return behavior is not required. The description covers parameters, usage constraints, and examples. It could mention interaction with sibling tools more explicitly, but is largely complete.

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

Parameters5/5

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

Schema coverage is 0%, yet the description provides a detailed 'Args' section explaining plan_id, transactions (with subfields), and exclude_fields. This adds significant meaning beyond the bare schema, fully compensating.

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?

The description explicitly states 'Update multiple transactions in a single API call.' It specifies verb, resource, and scope, and contrasts with single-transaction update via sibling tools. It also gives use cases like bulk recategorization.

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 explains when to use (bulk operations) and lists constraints (must provide id or import_id, sparse update, no subtransactions on existing split, no future-dated transactions). It does not explicitly state when not to use, but the context is clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pragprogrammer/mcp-ynab'

If you have feedback or need assistance with the MCP directory API, please join our Discord server