Split a transaction across multiple categories. Provide the transactionId and an array of splits whose amounts sum to the transaction total. Replaces any existing splits on the transaction.
| Name | Required | Description | Default |
|---|---|---|---|
| splits | Yes | Split portions — amounts must sum to the full transaction amount | |
| transactionId | Yes | ID of the transaction to split |
Changes observed during successful MCP inspections.
Input schema / properties / splits / items / properties / note / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 100,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / splits / items / properties / amount / descriptionPrevious value: -"Amount for this split portion (decimal)"New value: +"Amount for this split portion (decimal, greater than 0)"Input schema / properties / splits / items / properties / amount / exclusiveMinimumAdded value: +0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses that existing splits are replaced (a destructive overwrite) and imposes the sum-equals-total constraint, but it omits permission requirements, what happens if amounts don't sum correctly, atomicity, and the response shape.
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?
Three tight sentences with zero waste; the core action and the critical overwrite warning are front-loaded before the parameter guidance.
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 mutation tool with no annotations and no output schema, the description covers the essential semantics (sum constraint and replacement of existing splits). It still leaves meaningful gaps around error behavior on mismatched sums, permissions, and what the operation returns, which an agent would need to call it confidently.
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 description coverage is 100%, so both parameters and nested split fields are already documented, including the sum constraint. The description restates the sum-to-total rule but adds no syntax or format detail beyond the schema, so baseline 3 is appropriate.
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 states a specific verb and resource ('Split a transaction across multiple categories'), which is unambiguous and clearly distinct from siblings like update_transaction or delete_split. An agent can identify the operation without opening the schema.
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?
It explains the invocation form (provide transactionId and splits summing to the total) and that existing splits are replaced, which implies usage context. However, it never states when to use this versus update_transaction or delete_split, nor any prerequisites or conditions that select this tool over alternatives.
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.