rec_unmatchUndo a match, with a reason. The row goes back to how it was reviewed before; the payments are unmatched again. For a match that was wrong. The row returns to its earlier review (often not reviewed); say so to the person. Effects: match undone; the row back to its earlier review.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | Why it was wrong. | |
| match_id | Yes | The match, e.g. BM-0001. An existing bankrec_match id. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavioral detail beyond the annotations: the match is undone, payments become unmatched again, and the row returns to its earlier review state. This helps an agent understand the state change, though idempotency and rematch behavior are left to the annotations or unstated.
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?
The description is short and front-loaded, but it repeats the same effect multiple times. The first paragraph, the second paragraph, and the "Effects" line all restate that the row returns to its earlier review state.
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 two-parameter mutation tool with annotations covering read-only and destructive flags, the description gives an adequate account of the state transition. No output schema exists, so there is no return-value gap, though permission requirements are unstated.
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%, so the schema already documents both match_id and reason. The description reinforces that a reason is required, but it does not add format details or other meaning beyond what the schema provides.
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 and resource: "Undo a match". It makes the effect clear and is readily distinguishable from the sibling rec_match tool, which creates matches rather than reversing them.
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 an explicit usage condition: "For a match that was wrong." It does not explicitly name rec_match as the alternative or say when unmatching should not be used, but the context is clear.
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.