undo

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

No annotations are provided, so the description carries the full behavioral burden. It does not say whether undo is itself reversible, what happens when steps exceeds available history, whether it errors or no-ops, or whether combining undo with feature deletion is safe. Only the step granularity is disclosed.

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?

One front-loaded sentence with a parenthetical that earns its place by defining 'step'. No filler, though it is thin enough that a little more structure around failure behavior would not have hurt.

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?

The tool is simple: one optional integer parameter, no output schema, no nested objects. The description covers the core semantics but leaves out failure modes and reversibility, which matter for a state-mutating recovery operation.

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 'steps' parameter is already documented with a default. The description contributes the useful definition of what one step means (one modifying tool call), but adds no units, bounds, or error semantics beyond that. 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?

States a specific verb (Undo) and resource (the last modelling steps), and adds the crucial clarification that each modifying tool call counts as one step. An agent can distinguish this from delete_feature or set_expression, though no sibling is named explicitly.

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 never says when to prefer undo over alternatives such as delete_feature or editing an expression directly, nor does it state prerequisites like an existing undo history. Usage is only implied by the modelling context.

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