undo_last

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so safety profile is covered and the description does not contradict it. The description does add genuinely non-obvious context by defining undo granularity as one mutating tool call. It stops short of stating the failure behavior (empty history) or whether undo itself can be undone.

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 short sentences: the action first, then the non-obvious granularity rule. No repetition of the tool name, no filler, nothing to cut.

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, non-destructive mutation with no output schema, the definition covers what is acted on and the unit of reversion. The only meaningful gap is the absence of any statement about the result of the call or behavior on an empty undo stack.

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?

There are zero parameters, so there is nothing for the description to disambiguate and the baseline is a 4. The description correctly spends no words on parameters.

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?

"Undo the last change in Live" names a specific verb and resource, and no sibling tool overlaps with it. The second sentence sharpens the scope by defining what counts as one undo step, so the agent knows exactly what one call reverts.

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 purpose implies when to call it (to revert a prior mutation), and the 'each tool call that changes the Set is one undo step' line hints at how to reason about rollback depth. However, there is no explicit guidance on when not to use it, no mention of how to undo multiple steps, and no note on what happens when the undo history is empty.

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