Tally

Record an expense

record_expense

Record a payment made for shared household expenses, noting who paid and how to split the cost among members.

Instructions

Record that someone paid for something on the household's behalf. This is the main tool: use it the moment the user mentions paying.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "amount": "<amount>",
      "description": "<description>"
    },
    "name": "record_expense"
  }
}

Input Schema

Name	Required	Description
`amount`	Yes	What was paid, e.g. '42.50'
`shares`	No	Name to amount, when people owe different amounts. Must sum to the total.
`paid_by`	No	Who paid. Omit when the speaker paid.
`description`	Yes	What it was for, e.g. 'dinner'
`split_between`	No	Who shares it. Omit to split across the whole household.
`idempotency_key`	No	Repeat unchanged when resending; omit otherwise.

Output Schema

Name	Required	Description	Default
`settle`	Yes
`summary`	Yes
`balances`	Yes
`household`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 8, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already flag non-read-only, non-idempotent, and non-destructive behavior, so the safety profile is covered. The description adds no side-effect detail such as altering household balances or interacting with undo_last, but it does clarify that the expense is on the household's behalf. Given the annotation coverage, this is adequate but thin.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and a direct usage trigger. Every word earns its place and there is no filler or repetition.

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 a rich output schema and fully documented parameters, the description does not need to explain return values or every field. The trigger condition plus schema-level idempotency guidance is enough for correct invocation. The only minor gap is silence on the effect on balances, but that does not block usage.

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

Parameters3/5

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

Schema coverage is 100%, so the schema fully documents amount, paid_by, description, split_between, shares, and idempotency_key. The description only loosely mirrors these concepts ('someone paid for something') without adding format, constraint, or default details. The baseline of 3 is appropriate because the schema carries the parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear action and resource: record a payment made on the household's behalf. 'This is the main tool' signals it is the default expense-capture tool, which helps distinguish it from balance and activity siblings. It could be more explicit about not being for settlement or queries, but the core purpose is unambiguous.

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 instruction 'use it the moment the user mentions paying' is an explicit trigger condition. No exclusions or alternative routing are provided, but the sibling set makes the write-vs-read distinction easy to infer. This meets the clear-context level, just without formal when-not guidance.

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

Deploy Server