Skip to main content
Glama
trustxai

amazing-splitwise-mcp

by trustxai

splitwise_resolve_friend

Read-onlyIdempotent

Turn a friend's name or email into their Splitwise user ID with ranked fuzzy matches, confirming probable candidates before creating expenses, adding group members, or deleting friends.

Instructions

Turn a friend's name (or email) into their Splitwise user id, with ranked fuzzy candidates.

Calls GET /get_friends (not cached — friends change) and scores every friend with difflib.SequenceMatcher on case- and accent-folded text: the best of "first last", the first name, the last name, the email local-part and the full email. Returns the top limit candidates with their scores.

A friend is resolved ONLY on an exact match (1.000 on one of those fields, for exactly one friend, and no other friend's name or email starting with the query). A wrong id here is a wrong person — the expense, the group membership or the deletion lands on someone else — so a close-but-not-exact candidate ("Daniela" vs "Daniel", 0.923) is reported as probable and must be confirmed with the user. No fuzzy candidate is offered for a query under 4 characters or whose numbers differ.

When to Use:

  • Before splitwise_create_expense, splitwise_add_user_to_group, splitwise_get_friend or splitwise_delete_friend, when the user named a person ("split it with Jon").

When NOT to Use:

  • For balances with each friend — use splitwise_get_balances / splitwise_get_friends.

  • For groups or categories — use splitwise_resolve_group / splitwise_resolve_category.

  • Someone who is not your friend yet: they will not be listed — add them with splitwise_create_friend.

Returns: The resolution line plus a markdown table (rank, First Last (id N), email, score, matched on); or, with response_format json, {query, resolution, ambiguous_count, reason, resolved, probable, candidates: [{id, first_name, last_name, email, score, matched_on}]} where resolution is exact | probable | ambiguous | none, ambiguous_count (always present, 0 unless ambiguous) says how many candidates are in contention, resolved is set only for exact, and probable only for probable.

Examples: params = {"query": "Jon"} params = {"query": "maria garcia", "limit": 3, "response_format": "json"}

Error Handling: A 401 means the API key is missing or was regenerated. With no friends at all the tool says so. Anything but exact means: ask the user, do not pick.

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 cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond them: the endpoint is uncached, the scoring algorithm, the exact-match-only resolution rule, the danger of a wrong id, and that sub-4-character or digit-differing queries get no fuzzy candidate. This is exactly the extra context annotations cannot carry.

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?

Long but well-sectioned (purpose, when-to-use, when-not-to-use, returns, examples, error handling) with the core purpose front-loaded. Every section adds distinct value; only minor tightening 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?

Covers the ambiguity/resolution model, the exact/probable/ambiguous/none states, error handling (401, empty friend list), and usage examples. An agent has everything needed to call it correctly and to know not to auto-pick a fuzzy match.

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?

Reported schema coverage is 0%, but the description compensates: it explains that `limit` bounds the top-N candidates, that `query` is 'the name as the user said it,' and fully specifies the `response_format`='json' payload shape. Semantics for each param are grounded in behavior rather than just restated.

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+scope: 'Turn a friend's name (or email) into their Splitwise user id, with ranked fuzzy candidates.' It is immediately distinguishable from siblings like splitwise_get_friends or splitwise_resolve_group, which are named explicitly later.

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?

Dedicated 'When to Use' and 'When NOT to Use' sections name the prerequisite tools (splitwise_create_expense, splitwise_add_user_to_group, etc.) and route non-friend lookups to splitwise_get_balances, splitwise_resolve_group, and splitwise_create_friend. Explicit alternatives with conditions.

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