undo

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

Annotations already declare destructiveHint=true and openWorldHint=false, so the agent knows this mutates scene state locally. The description adds useful nuance that only 'successful' mutations are reverted, implying failed operations do not consume the undo. It does not, however, state what happens when there is no prior mutation, whether the undo itself can be reverted (no redo), or that the current state is discarded.

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?

A single tight sentence with the action front-loaded and no filler. Every clause ('before', 'most recent', 'successful') carries distinct meaning about scope.

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 parameters and an output schema present, the description need not explain return values, and it covers the essential behavior. The remaining gap is edge-case behavior — what happens with an empty undo history, and whether multiple successive undos walk further back — which an agent might reasonably want to know.

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 tool takes zero parameters, so there is no parameter semantics to explain; the baseline for a parameterless tool is 4. The schema is fully closed (additionalProperties: false), so nothing is left ambiguous on the input side.

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 gives a specific verb ('Restore'), an explicit resource ('the scene'), and a precise temporal scope ('before the most recent successful mutation'), which effectively defines undo. It does not explicitly distinguish itself from siblings like 'clear' or 'delete' (other state-changing operations), so it stops short of a 5.

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?

Usage is only implied: an agent can infer it should call this after an unwanted change, but there is no explicit when-to-use/when-not guidance, no mention of what to do if nothing has been mutated, and no named alternatives. The phrase 'most recent successful mutation' does hint at single-step semantics, which is some guidance.

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