undo

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this mutates state irreversibly. The parenthetical adds genuinely useful behavioral context about undo granularity (one tool call = one step), but the description says nothing about what happens when the undo stack is empty or whether the call fails or silently no-ops.

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 front-loaded sentence with zero waste, where the parenthetical carries real information rather than padding.

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 zero-parameter, annotated mutation tool with no output schema, the description covers purpose, granularity, and the implicit mutating nature. The only gap is empty-stack / failure behavior, which is a minor omission given how little an agent needs to invoke this correctly.

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 the baseline of 4 applies; there is no parameter syntax an agent could get wrong and nothing the description needs to compensate for.

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 its exact scope (the last step in SketchUp), and the parenthetical nails the granularity of that step. No sibling in the list competes with it, so no differentiation is needed, but the description itself makes no such routing explicit.

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?

There is no undo/redo alternative among the siblings to route between, and the parenthetical implies use after any model-editing call, but the description never states when to invoke it or what condition (e.g. nothing left to undo) makes it inappropriate.

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