Undo the last entry

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already flag destructiveHint=true, so the agent knows this is a destructive operation. The description reinforces that by saying it 'reverses' an entry. It does not explicitly state that only the most recent entry is affected (though that is implied by the name and description) or whether the undo itself can be undone, but this is a minor gap given the simplicity of the tool.

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 a single, concise sentence that states the action, the target, and a contextual trigger. There is no extraneous information, and the structure is clean and easy to parse. It fits the tool's simple nature perfectly.

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 simple undo operation, the description is complete. It tells what the tool does, when to use it, and (via annotations) that it is destructive. No output schema is provided, but that is acceptable given the tool's nature. An agent has enough context to decide when and how to invoke it without further clarification.

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?

The only parameter, idempotency_key, is fully described in the schema with a clear explanation: 'Repeat unchanged when resending; omit otherwise.' This is a standard idempotency key instruction and covers the parameter's purpose and usage. With 100% schema coverage and an accurate description, there is no ambiguity.

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 clearly states the tool's function: 'Reverse the most recent expense or payment.' The verb 'Reverse' and resource 'most recent expense or payment' are specific and unambiguous. It also stands apart from sibling tools like record_expense or settle_up by being the only undo operation, so an agent can easily distinguish it.

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 includes an explicit usage scenario: 'for when something was misheard.' This tells the agent when to invoke the tool (e.g., after an incorrect voice entry). However, it could more broadly state 'when an incorrect entry was made' and does not mention any limitations or prerequisites (e.g., that an undoable entry must exist), so it leaves a little room for interpretation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.