Skip to main content
Glama
Sign In
splitwise-mcp

splitwise-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

sw_list_friends

Read-only

Lists Splitwise friends with IDs, names, emails, status, and balances so you can resolve a friend to a user_id before adding them to groups or splitting expenses.

Instructions

List all Splitwise friends. Use this to resolve a friend's name to a user_id before adding them to a group or building a custom expense split. The compact default returns id, name (first_name + last_name joined), email, registration_status and any non-empty balance per friend; pass view:'full' for Splitwise's raw records, which keep first_name and last_name separate.

Input Schema

NameRequiredDescriptionDefault
viewNoResponse shape. compact returns {id, name, email, registration_status, balance} per person — `name` is first_name + last_name joined, so the separate fields are on "full" only; "full" returns Splitwise's whole record. "brief" answers "what do I owe / who owes me": one line per friend with an outstanding balance (name — no date — "owes you <amount>" or "you owe <amount>"), inside the untrusted-data envelope, then a "-- N settled up" note; "-- none" when nothing is owed either way.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.6.0
    • changedInput schema / properties / view / description
      Previous value: -"Response shape: \"compact\" (default) drops fields the response already carries elsewhere; \"full\" returns every field this server understands. compact returns {id, name, email, registration_status, balance} per person — `name` is first_name + last_name joined, so the separate fields are on \"full\" only; \"full\" returns Splitwise's whole record."New value: +"Response shape. compact returns {id, name, email, registration_status, balance} per person — `name` is first_name + last_name joined, so the separate fields are on \"full\" only; \"full\" returns Splitwise's whole record. \"brief\" answers \"what do I owe / who owes me\": one line per friend with an outstanding balance (name — no date — \"owes you <amount>\" or \"you owe <amount>\"), inside the untrusted-data envelope, then a \"-- N settled up\" note; \"-- none\" when nothing is owed either way."
    • changedInput schema / properties / view / enum
      Previous value: -[
-  "compact",
-  "full"
-]New value: +[
+  "compact",
+  "full",
+  "brief"
+]
  2. Changed1 schema field changedv3.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. Changed2 schema fields changedv2.4.0
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / properties / view
      Added value: +{
+  "description": "Response shape: \"compact\" (default) drops fields the response already carries elsewhere; \"full\" returns every field this server understands. compact returns {id, name, email, registration_status, balance} per person — `name` is first_name + last_name joined, so the separate fields are on \"full\" only; \"full\" returns Splitwise's whole record.",
+  "enum": [
+    "compact",
+    "full"
+  ],
+  "type": "string"
+}
  4. First observedv2.1.5

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), so the bar is lower, and the description adds real context: what fields the default payload carries, that name is first_name + last_name joined, and that 'full' preserves Splitwise's raw record shape. It doesn't discuss pagination, rate limits, or auth scope, which keeps it from a 5.

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?

Three sentences, front-loaded with purpose, then usage, then return shape — a sensible ordering with no filler. There is mild duplication between the description's view-mode summary and the schema's enum text, which keeps it from a 5.

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 burden of explaining returns and does so for both views, including the joined-name quirk that would otherwise surprise a caller. For a single-parameter read-only list tool, an agent has everything needed to invoke it correctly.

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 description coverage is 100%, so the baseline is 3; the description goes beyond it by disclosing that 'compact' is the default view — a fact absent from the schema, which lists the enum but declares no default. It otherwise largely restates the enum meanings already documented in the schema.

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?

"List all Splitwise friends" names a specific verb and resource, and the follow-on clause pins down the downstream intent (resolving a name to a user_id). It is easy to distinguish from sw_get_user (single lookup) and sw_create_friend (mutation) without opening any schema.

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?

It gives a concrete when-to-use trigger: resolve a friend's name to a user_id before adding them to a group or building a custom split. It does not explicitly name an alternative (e.g. sw_get_user for a known id) or state when not to call it, so it falls short of a 5.

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

Deploy Server

Other Tools