Skip to main content
Glama

finance

by com.zoninga
OverviewDiscussionsAdmin

Transactions: Bulk delete transactions

bulk_delete_transactions
Destructive
    Delete multiple transactions at once with per-row rule-21 semantics.

    Each row gets the same treatment as a single-transaction delete:
    manual transactions are soft-deleted (balance reversed, restorable
    for 7 days); Plaid-originated transactions
    are hard-deleted (restoring them after Plaid has moved on creates
    ledger drift). Future-dated (unapplied) rows skip balance reversal.

    IDs that are missing or belong to another user are skipped and
    reported; those rows are left untouched.

    Args:
        transaction_ids: List of transaction IDs to delete (max 100)

    Returns:
        Per-id results with `undoable` flags, counts, and a note about
        the 7-day undo window for soft-deleted rows.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
transaction_idsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes far beyond the annotations by disclosing the core behaviors: soft-delete with balance reversal and 7-day restorability for manual rows, hard-delete for Plaid rows and the drift rationale, skipped balance reversal for future-dated rows, and silent skipping/reporting of missing or foreign-user IDs. These are exactly the mutation consequences an agent needs and none contradict the destructive/non-idempotent hints.

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-loads the core action, then uses clear Args/Returns structure. The prose is slightly long but each sentence conveys a distinct rule; little is wasted.

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 carries the return contract (per-id results, undoable flags, counts, 7-day undo note) and fully covers the destructive semantics, authorization edge cases, and edge-case row handling. Nothing essential to correct invocation is missing.

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 0% and the single array parameter carries no schema description, but the description supplies the crucial 'max 100' bound the schema omits and clarifies the parameter is a list of transaction IDs. That is real added meaning over an otherwise bare integer array.

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 and resource (delete multiple transactions) plus the operational scope ('at once'), which cleanly separates it from the single-row delete_transaction sibling. An agent can identify the tool's function 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 Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The bulk/at-once framing implies when this tool applies, and the per-row semantics inform decisions, but it never names the alternative (delete_transaction for single rows, undo_transaction for recovery) or states when-not to use it. Usage is inferred rather than instructed.

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

All finance toolsInspect
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