Skip to main content
Glama
trustxai

amazing-splitwise-mcp

by trustxai

splitwise_add_user_to_group

Add a friend by user ID or invite a new person by name and email to an existing Splitwise group. Requires write access enabled.

Instructions

Add a person to a group, by user id or by inviting a name + email. 🔒 write.

Calls POST /add_user_to_group with group_id plus EITHER user_id OR all of first_name, last_name, email (a oneOf, checked locally before any call; an invited email may receive a Splitwise invitation). Splitwise answers HTTP 200 even on failure; the client turns success: false / non-empty errors into an error, and the person is reported as added only when the body says success: true and returns the user. Refused with Error: … writes are disabled unless SPLITWISE_ALLOW_WRITES=1. Undo: splitwise_remove_user_from_group with the returned user id.

When to Use:

  • To add a friend (user id) or a new person (name + email) to an existing group.

When NOT to Use:

  • To create a group with its members in one call (use splitwise_create_group).

  • To find a friend's user id by name (use splitwise_resolve_friend first), or a group's id by name (use splitwise_resolve_group).

Returns: A confirmation with the user Splitwise returned (First Last (id N)) and its success value.

Examples:

  • params = {"group_id": 12345, "user_id": 5823}

  • params = {"group_id": 12345, "first_name": "Ana", "last_name": "Diaz", "email": "ana@example.com"}

Error Handling: Both or neither identity → rejected before the call; success: false → Error: Splitwise rejected the request ...; 403 → you are not a member of the group.

Input Schema

NameRequiredDescriptionDefault
paramsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A5/5.0
Behavior5/5

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

Annotations only give generic hints (readOnlyHint=false, openWorldHint=true, idempotentHint=false), but the description goes well beyond: it discloses the SPLITWISE_ALLOW_WRITES=1 auth gate, local oneOf validation before any call, the fact that HTTP 200 can still mean failure and how success is determined, the 403 case, and the undo tool with the returned user id. This is exemplary behavioral disclosure for a mutation.

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?

Sections are clearly headed and front-loaded (what it does, endpoint, then when/when-not, returns, examples, errors). The length is justified by genuinely distinct information — auth gate, error semantics, undo path — with no filler.

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 already having an output schema, the description still summarizes the return shape ('First Last (id N)' plus success value), and covers auth, validation, failure, and reversal. For a write tool with this complexity, nothing an agent needs to call it correctly 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 carries no schema description (0% coverage signal), the description fully compensates by explaining the oneOf identity semantics (user_id OR first_name+last_name+email), that both-or-neither is rejected, and giving concrete param examples. It adds meaning the schema's per-field descriptions do not capture (the combination constraint).

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 ('add a person') and resource ('to a group') plus the two identity modes (existing user id vs. name+email invite). It explicitly names siblings it is not (splitwise_create_group, splitwise_resolve_friend, splitwise_resolve_group), so an agent can distinguish it without opening other schemas.

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?

Has explicit 'When to Use' / 'When NOT to Use' sections naming concrete alternatives and the prerequisite resolve steps for finding ids. The conditions that select this tool versus others are spelled out, not inferred.

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