Skip to main content
Glama
trustxai

amazing-splitwise-mcp

by trustxai

splitwise_create_comment

Post a comment on a Splitwise expense to leave a shared note everyone on it can see. Writes must be enabled (SPLITWISE_ALLOW_WRITES=1).

Instructions

Add a comment to a Splitwise expense.

Write — refused unless SPLITWISE_ALLOW_WRITES=1. Calls POST /create_comment with expense_id and content. Everyone on the expense can see the comment. Not idempotent: calling it twice posts the comment twice.

When to Use:

  • To leave a note on an expense ("paid in cash", "includes the tip").

When NOT to Use:

  • To change the expense's own description or notes — use splitwise_update_expense.

  • To read existing comments — use splitwise_get_comments.

Returns: A confirmation echoing the comment Splitwise returned: its id, the expense id, the author, the type, the creation time and the text.

Examples:

  • params = {"expense_id": 51023, "content": "Paid in cash, settled at dinner."}

Error Handling: Refused with Error: … writes are disabled unless SPLITWISE_ALLOW_WRITES=1. A blank content is rejected before any call. 404 = the expense does not exist or was deleted; 403 = you are not part of it. On a timeout or 5xx the outcome is UNKNOWN — read the comments back with splitwise_get_comments before retrying, or the comment may be posted twice. Undo with splitwise_delete_comment.

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?

Goes well beyond the annotations: discloses the SPLITWISE_ALLOW_WRITES=1 gate, comment visibility ('everyone on the expense can see the comment'), non-idempotency with an explicit duplicate-post warning, 404/403 meanings, an UNKNOWN-outcome protocol for timeouts/5xx, and the undo path. The annotations (readOnlyHint=false, idempotentHint=false) are confirmed and enriched rather than merely restated.

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?

The write-gate and non-idempotency warnings are front-loaded in the first two paragraphs, then sectioned into When to Use / Returns / Examples / Error Handling. Dense but every block carries actionable information, and the labeled structure makes it skimmable.

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 mutating, non-idempotent, auth-gated tool this covers the failure modes an agent needs: write gating, visibility scope, duplicate-post hazard, status-code meanings, unknown-outcome recovery, and undo. An output schema exists, so the brief Returns line is a courtesy rather than a gap.

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 reported at 0%, so the description must carry the load; it names both `expense_id` and `content`, notes content must be non-blank plain text, and supplies a literal params example showing shape and types. It stops short of explaining id format constraints or the max comment length, so it compensates well but not exhaustively.

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 and resource ('Add a comment to a Splitwise expense') and immediately distinguishes itself from siblings by naming splitwise_update_expense and splitwise_get_comments as the tools for adjacent jobs. An agent can route correctly 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit 'When to Use' and 'When NOT to Use' sections with concrete triggers ('leave a note on an expense') and named alternatives for the two nearest confusable operations. Nothing about tool selection 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.