Skip to main content
Glama
trustxai

amazing-splitwise-mcp

by trustxai

splitwise_get_balances

Read-onlyIdempotent

Summarize who owes you and whom you owe per friend and currency, plus net totals for settling up.

Instructions

Summarise who owes you and whom you owe, per friend and per currency.

Calls GET /get_friends once and, from each friend's balance list, renders every non-zero balance per currency, plus per-currency totals: how much you are owed, how much you owe, and the net. Friend balances already combine group and non-group expenses. Sign convention: positive = the friend owes you (owed to you); negative = you owe the friend. Zero balances are hidden unless include_zero is true; the optional currency filter keeps a single currency (applied locally — the endpoint takes no filter). An amount Splitwise sends that is not a plain decimal, or an entry with no currency, is shown raw and flagged, and left out of the totals.

When to Use:

  • "How much am I owed / do I owe overall?", "who owes me money?", "my USD balance".

  • Before settling up, to see every open balance in one call.

When NOT to Use:

  • For balances inside ONE group and who pays whom there (use splitwise_get_group_balances).

  • For friend profiles, e-mails or per-group breakdowns (use splitwise_get_friends / splitwise_get_friend).

  • To find a friend's id from a name (use splitwise_resolve_friend).

Returns: Markdown: the sign convention, a totals table (Currency | You are owed | You owe | Net) and a table of friends (First Last (id N) with e.g. +12.50 USD, -3.00 PEN; with include_zero, settled up or no USD balance), capped at 50 rows (totals cover every friend except the flagged entries). JSON: {sign_convention, currency_filter, totals: {CUR: {owed_to_you, you_owe, net}}, unparsed: [{friend_id, currency_code, amount, reason}], friend_count, friends: [raw friend objects]} with you_owe as a positive magnitude and money as 2-decimal strings.

Examples:

  • params = {}

  • params = {"currency": "USD"}

  • params = {"include_zero": true, "response_format": "json"}

Error Handling: A bad currency (not 3 letters) is rejected before any call. 401 means the API key is missing or was regenerated; 429 means back off (Retry-After). Errors come back as an Error ... string.

Input Schema

NameRequiredDescriptionDefault
paramsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds substantial behavior beyond them: the underlying call (GET /get_friends), the sign convention that positive means owed-to-you, that the currency filter is applied locally because the endpoint takes no filter, that malformed amounts are shown raw, flagged, and excluded from totals, and the 401/429/Retry-After error semantics.

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 with a one-line summary and cleanly sectioned (When to Use / When NOT / Returns / Examples / Error Handling), so navigation is fast. However, the Returns section is long and partly restates what an existing output schema already conveys, so a little trimming is possible.

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?

For a read tool with annotations, an output schema, and only one nested params object, the description covers everything an agent needs: scope, alternatives, filtering semantics, output shape for both formats, the 50-row cap, and failure modes. Nothing material 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?

Although the top-level 'params' object has no schema description (0% coverage per the signal), the description carries the parameters: it explains include_zero's effect (zero balances hidden unless true), the currency filter being a 3-letter local filter that is rejected before any call, and what response_format switches between, plus three concrete parameter examples.

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 opening sentence states a specific verb and resource ('Summarise who owes you and whom you owe, per friend and per currency') and the When NOT to Use block explicitly routes to splitwise_get_group_balances for single-group balances. An agent can distinguish it from every sibling 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?

Explicit 'When to Use' triggers ('who owes me money', before settling up) and an explicit 'When NOT to Use' list naming the three alternative siblings (splitwise_get_group_balances, splitwise_get_friends/get_friend, splitwise_resolve_friend) with the condition that selects each. 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.