Skip to main content
Glama
trustxai

amazing-splitwise-mcp

by trustxai

splitwise_delete_expense

DestructiveIdempotent

Delete a duplicate or mistaken Splitwise expense by ID. The expense is kept as deleted so it can be restored, and all participants' balances update accordingly.

Instructions

Delete an expense (Splitwise keeps it as deleted; restore with splitwise_undelete_expense).

Calls POST /delete_expense/{id}. Refused with Error: … writes are disabled unless SPLITWISE_ALLOW_WRITES=1 (enforced by the server's client). Deleting changes every participant's balances. Restore with splitwise_undelete_expense and the same id.

When to Use:

  • Remove a duplicate or mistaken expense.

When NOT to Use:

  • To fix an amount or split (use splitwise_update_expense).

  • To remove a whole group with its expenses (use splitwise_delete_group).

Returns: The success value Splitwise returned for the deletion, and the undo hint.

Examples:

  • params = {"expense_id": 3456789012}

Error Handling: Splitwise answers 200 even when it refuses — the client turns success: false / a non-empty errors into Error: Splitwise rejected the request…. 404 → wrong id; 403 → not your expense.

Input Schema

NameRequiredDescriptionDefault
paramsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructive/idempotent/openWorld, and the description adds value beyond them: the delete is a recoverable soft delete, it requires SPLITWISE_ALLOW_WRITES=1 or the server refuses, it mutates every participant's balances, and refusal arrives as HTTP 200 with success:false. This is exactly the extra behavioral context the annotations cannot convey.

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 header-based layout is front-loaded and scannable, and each section (endpoint, gating, usage, returns, example, errors) earns its place. The undo/restore instruction is stated twice (opening parenthetical and later), which is mild redundancy.

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?

Despite an output schema existing, the definition covers everything an agent needs: write gating, blast radius on balances, the undo path, the id source, and the error decoding for 200/403/404 responses. Nothing material is missing for a destructive one-parameter call.

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?

Only one nested parameter and the schema names it with a hint about its origin, but reported coverage is 0%, so the description compensates with a concrete example ({"expense_id": 3456789012}) and ties 404/403 error meanings to the id. It stops short of explaining any format constraint, but with a single required integer that is a minor gap.

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 an expense') plus the crucial soft-delete semantics, and explicitly distinguishes itself from splitwise_update_expense, splitwise_delete_group, and splitwise_undelete_expense. An agent can identify this tool among 32 siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Provides explicit 'When to Use' (duplicate or mistaken expense) and 'When NOT to Use' sections that name the correct alternative tool for each excluded case (update for amount/split fixes, delete_group for whole-group removal). Nothing is left to inference.

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