finance

Transactions: List transactions

list_transactions

Read-onlyIdempotent

    List transactions with optional filters.

    Args:
        account_id: Filter by account ID
        category_name: Filter by category name (case-insensitive)
        transaction_type: Filter by type (deposit or withdrawal)
        start_date: Start date in YYYY-MM-DD format
        end_date: End date in YYYY-MM-DD format
        search: Search in description
        tag_name: Filter by tag name (case-insensitive)
        limit: Maximum number of transactions to return (default: 50, max: 200)
        offset: Number of transactions to skip for pagination (default: 0)
        count_only: If true, return only the total count and totals without transaction details (faster for counting)

    Returns:
        List of transactions plus ``total_count`` (untruncated) and pagination info.
        Each row carries ``economic_class`` (income / expense / transfer /
        balance_sheet), the income-vs-spending classification. Raw
        ``transaction_type`` differs from it on debt accounts: a credit-card
        CHARGE is stored as ``deposit`` and a card PAYMENT as ``withdrawal``.
        ``totals`` (deposits/withdrawals/net) is aggregated over the ENTIRE matching
        window in BOTH normal and count_only modes — NOT just the returned page — so a
        paginated read reports the full period's income/expenses. The current page's
        subtotal is the sum of the per-row ``amount`` values.

    SCOPE NOTE: this is a raw transaction listing and INCLUDES rows on
    archived (inactive) accounts — like the CSV export, it's the user's
    complete history. The cash-flow, spending, uncategorized-summary and
    other analytics reports EXCLUDE archived-account transactions, so their
    totals differ from a raw list over the same window when the user has
    archived accounts. Filtering by an active ``account_id`` matches the
    analytics scope.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`offset`	No
`search`	No
`end_date`	No
`tag_name`	No
`account_id`	No
`count_only`	No
`start_date`	No
`category_name`	No
`transaction_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 22, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already cover readOnly/idempotent/non-destructive, yet the description adds substantial behavioral context beyond them: totals are aggregated over the ENTIRE matching window in both normal and count_only modes, economic_class differs from raw transaction_type on debt accounts (charges stored as deposit, payments as withdrawal), and archived accounts are included. These are non-obvious traits an agent cannot infer elsewhere.

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?

Front-loaded purpose followed by clearly delimited Args/Returns/SCOPE sections, and every block earns its place given the 10 undocumented params and absent output schema. It is somewhat long and the Args list partly restates parameter names, but the added semantics justify the length.

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?

With no output schema, the description fully specifies the return shape (rows, total_count untruncated, pagination info, economic_class, totals aggregated over the whole window vs page subtotal). Combined with the scope caveat, nothing an agent needs to invoke or interpret this tool is missing.

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 description coverage is 0%, so the description carries the full burden and does so well: it documents every parameter's meaning plus format ('YYYY-MM-DD'), case-insensitivity, default 50 / max 200 for limit, pagination semantics for offset, and the speed/count_only tradeoff. This fully compensates for the empty schema.

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?

States a specific verb + resource ('List transactions with optional filters') and the SCOPE NOTE explicitly differentiates it from sibling analytics reports (cash-flow, spending, uncategorized-summary) and the CSV export by explaining it includes archived-account rows. An agent can distinguish this raw-listing tool from summary tools without opening any 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 SCOPE NOTE tells the agent when this tool's output will diverge from analytics reports and how to reconcile them ('filtering by an active account_id matches the analytics scope'). It gives clear contextual guidance, though it never states an explicit 'use this instead of X' rule, so it stops 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.

All finance tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?