Skip to main content
Glama

ynab_reconcile_account

Idempotent

Reconcile your YNAB account with bank CSV transactions to match entries, detect discrepancies, and optionally auto-create or clear transactions.

Instructions

Guided account reconciliation: match bank CSV transactions to YNAB, detect discrepancies, and optionally execute bulk create/update/unclear operations.

Args:

  • budget_id (string, optional): Budget UUID. Omit to use the default budget.

  • account_id (string, required): Account UUID to reconcile.

  • csv_file_path or csv_data (string, required): Bank export file path or inline CSV text.

  • statement_balance (number, required): Ending balance from the bank statement (dollars). For credit cards and other liability accounts, pass a negative value (e.g. -6143.27 means you owe $6,143.27).

  • statement_end_date (string, optional): Statement closing date (YYYY-MM-DD). Filters CSV and triggers balance verification. Auto-detected from CSV if omitted.

  • match_strictness (string, optional): Matching sensitivity — "loose" (more matches), "normal" (default), or "strict" (fewer false positives).

  • sign_convention (string, optional): How to treat CSV amount signs — "auto" (default, detects from data), "invert" (negate all amounts), "as_is" (use amounts unchanged). Useful when auto-detection fails for liability accounts.

  • dry_run (boolean, optional): Preview actions without executing. Default: true.

  • auto_create_transactions (boolean, optional): Auto-create missing transactions. Default: false.

  • auto_update_cleared_status (boolean, optional): Auto-mark matched transactions as cleared. Default: false.

  • auto_unclear_missing (boolean, optional): Auto-mark statement-missing cleared transactions as uncleared when reconciliation remains unbalanced. Default: false.

  • max_suggestions_in_output (number, optional): Limit unmatched items and suggestions shown in the human report. Default: 20.

Returns: human-readable reconciliation narrative + structured JSON (unmatched_bank, unmatched_ynab, suggestions, execution_summary when actions are performed).

Examples:

  • Preview reconciliation: set dry_run=true (default)

  • Execute: set dry_run=false and explicitly enable the write flags you want, e.g. auto_update_cleared_status=true

Write safety: call without confirmation_token to preview. Execute the identical validated request with the short-lived confirmation_token returned by that preview.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runNo
csv_dataNo
budget_idNo
account_idYes
csv_formatNo
csv_file_pathNo
sign_conventionNoauto
match_strictnessNonormal
auto_adjust_datesNo
statement_balanceYes
confirmation_tokenNoShort-lived, single-use token returned by the immediately preceding preview of this exact validated request.
statement_end_dateNo
date_tolerance_daysNo
auto_unclear_missingNo
auto_create_transactionsNo
max_suggestions_in_outputNo
auto_update_cleared_statusNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
humanYes
structuredYes
Behavior4/5

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

Annotations indicate non-read-only and idempotent behavior. The description adds critical behavioral context: the write safety mechanism requiring a preview first, the default dry_run=true, and the confirmation_token pattern. This transparency goes beyond the structured annotations.

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 somewhat lengthy but well-structured: a clear opening sentence, followed by organized parameter descriptions, return value outline, examples, and safety notes. Every section adds value, though slight tightening could improve conciseness.

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

Completeness5/5

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

Given the tool's complexity (17 parameters, output schema, nested objects), the description is comprehensive. It covers parameter semantics, return format (narrative + JSON), usage examples, and the unique confirmation_token workflow. The presence of an output schema reduces the need to detail return values, but the description still provides useful context.

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?

With only 6% schema description coverage, the description compensates thoroughly by explaining most parameters in detail. For example, it clarifies that statement_balance should be negative for liability accounts, and explains the sign_convention options. This adds substantial meaning beyond the schema definitions.

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 clearly states the tool's purpose: 'Guided account reconciliation: match bank CSV transactions to YNAB, detect discrepancies, and optionally execute bulk create/update/unclear operations.' This provides a specific verb and resource, distinguishing it from siblings like ynab_create_transaction or ynab_export_transactions.

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 offers extensive usage guidance, including the two-phase preview-execute workflow via confirmation_token, dry_run defaults, and write safety. While not explicitly contrasting with alternatives, the explanation of when to preview vs. execute is clear and actionable.

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/dizzlkheinz/ynab-mcpb'

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