get_splitRead a split: participants, expenses, per-person balances and the shortest set of payments that settles everyone up.
| Name | Required | Description | Default |
|---|---|---|---|
| split | Yes | The split key, or the whole https://split.xuper.fun/k/<key> link. |
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | ||
| url | Yes | ||
| title | Yes | ||
| secure | Yes | ||
| entries | Yes | ||
| settled | Yes | ||
| currency | Yes | ||
| created_at | Yes | ||
| settlement | Yes | ||
| total_spent | Yes | ||
| participants | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint: true annotation already covers the safety profile (this is a read operation). The description adds value by disclosing what the read returns, including the computed per-person balances and the shortest settlement payment set—useful behavioral context beyond the bare annotation. There's no contradiction. It doesn't disclose things like whether the split must exist or error behavior, but for a read tool with the annotation present, this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, zero waste. It front-loads the verb ('Read'), specifies the resource, and enumerates the returned data compactly. Every element earns its place, and no filler or redundant phrasing exists.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter read tool with readOnlyHint annotation and an output schema present, the description is largely complete. It enumerates what the response includes (participants, expenses, balances, settlement set). Since the output schema exists, the description needn't detail the return structure further. Slight room to mention whether the key/link works for both input forms or if the split must exist, but it's otherwise thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%—the single 'split' parameter is documented in the schema as the split key or full link. The description doesn't add parameter-specific meaning beyond what the schema provides, but it doesn't need to since there's exactly one parameter with full coverage. The baseline of 3 for high schema coverage applies correctly here.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Read') with a clear resource ('a split') and enumerates what's returned: participants, expenses, per-person balances, and settlement payments. This clearly distinguishes it from the sibling tools, all of which are mutation-oriented (add_expense, update_split, delete_entry, etc.), so there's no ambiguity about this being the read operation. While it doesn't name a sibling explicitly, the contrast with the write-heavy siblings is obvious.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage as the retrieval tool for split details, and the sibling tools being all mutations makes the read-vs-write context clear. However, there's no explicit when-to-use or when-not-to-use guidance, nor mention of alternatives. It's a single-parameter, single-purpose tool, so heavy guidance isn't needed, but a note like 'use when you need to view balances or settlement calculations' would strengthen it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly distinct by resource and action (expense vs participant vs split vs payment). Minor ambiguity exists between update_entry and record_payment, since both modify existing entries, though their purposes (re-editing vs settlement) are documented. add_expense and record_payment could overlap conceptually since both record money movement, but descriptions clarify each.
All 11 tools follow a clean verb_noun pattern: add_expense, add_participant, create_split, delete_entry, get_split, record_payment, remove_participant, rename_participant, set_payment_methods, update_entry, update_split. The convention is fully consistent with no mixed styles or vague verbs.
11 tools is well within the ideal 3-15 range, and each earns its place by mapping to a distinct lifecycle operation across splits, participants, entries, and payments. The count is appropriately scoped for an expense-splitting domain and matched to the feature set described.
The surface covers the core lifecycle well: create/read/update for splits, add/remove/rename participants, and add/delete/update entries plus payment recording and settlement. The main gap is the explicit write operations only work on simple/accountless splits while secure splits are read-only, but that's a documented constraint rather than a missing tool. A dedicated 'duplicate_split' or 'list_splits' would be nice but isn't critical for the modeled flow.