undo_last_mutation

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

No annotations are provided, so the description must carry the behavioral burden. It does add useful behavior: FIFO semantics, same inversion behavior as undo_mutation, and dry_run support. However, it does not disclose side effects, permanence, failure behavior when the queue is empty, or what happens to the receipt after undoing – important gaps for a mutating 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?

Two front-loaded sentences with no wasted words. The action and scope come first, followed by semantic reference and dry_run support – each clause earns its place.

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?

With no output schema and no annotations, the description should explain return values, error cases, and safety implications. It omits what happens when there is no reversible mutation, whether the undo consumes the receipt, and what the tool returns. While sufficient for a simple one-parameter tool, these gaps make it only moderately complete.

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% and the single dry_run parameter is already fully described in the schema as 'Preview only: validate inputs and describe exactly what would change without performing it'. The description's mention of dry_run adds no new parameter semantics, so the baseline 3 applies.

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 ('Undo') with a specific resource ('most recent reversible mutation') and defines the scope via 'receipt FIFO'. It also references 'same inversion semantics as undo_mutation', which helps distinguish it from the broader undo_mutation sibling.

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 phrase 'most recent reversible mutation (receipt FIFO)' clearly indicates when this tool applies: for the latest mutation in the receipt queue. It references undo_mutation as a related alternative, though it does not explicitly say 'use undo_mutation for a specific receipt' or 'use undo_preview for previewing', so the guidance is contextual rather than fully explicit.

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