Reverses an incorrect manual transaction while preserving audit history. Use only with explicit user authorization; never silently deletes or hides records.
Reverse an incorrect manual transaction, preserving audit. Only on user authorization; do not silently delete or hide history.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| reason | Yes | ||
| request_id | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description reinforces the non-destructive nature by saying it preserves audit and does not hide history, which gives useful semantic context about a reversal rather than a delete. It does not explain the idempotency contract, the authorization mechanism, or what happens to the original transaction besides being preserved.
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?
Two compact sentences with the operation stated first and the safety constraint immediately after. No filler, no repetition.
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?
It is a mutating tool with no output schema and three fully undocumented required parameters, so the description carries the whole burden and does not meet it. Missing are the meaning of id versus request_id, the idempotency behavior, and what a successful reversal returns.
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 0% and all three parameters (id, reason, request_id) are required but undocumented in the schema. The description never mentions any parameter, so an agent must infer that 'id' is the transaction to reverse and that request_id is an idempotency key. That is a substantive gap given three required params.
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 pairs a specific action ('reverse') with a specific resource ('an incorrect manual transaction'), so the intent is unambiguous. It does not explicitly distinguish itself from siblings like budget_adjust_pool or budget_record, but the 'reverse a manual transaction' framing is distinctive enough to differentiate in practice.
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 gives one hard precondition ('Only on user authorization') and one prohibition ('do not silently delete or hide history'), which implies the reversal workflow. However, it never names an alternative sibling for other correction scenarios, nor does it state when the tool should not be used versus other budget tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.