document.undo

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

No annotations exist, so the description carries the full burden, and it discloses almost nothing: it does not say the operation mutates the document, what happens when the undo stack is empty (error vs no-op), how deep the undo history goes, or whether undo can itself be undone via redo. 'Most recent' is the one real behavioral detail, implying a single step rather than a multi-step revert.

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 short, front-loaded sentence with no filler. It is appropriately sized for a no-argument history operation.

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 call mechanics are trivial (no params, no output schema), so the description is nearly sufficient to invoke. What is missing is the surrounding context an agent needs to use it safely: failure behavior on an empty stack and the relationship to document.can_undo and document.redo.

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 nothing for the description to disambiguate. Baseline 4 applies for a no-arg tool.

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?

A specific verb (undo) plus the exact scope (the most recent command), so the agent knows this is a single-step history rollback rather than a bulk revert. It does not, however, distinguish itself from the very close siblings document.redo and document.can_undo, whose purposes sit right next to it.

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 guidance on when to call this versus document.redo, document.can_undo, or manual re-application of changes, and no mention of checking undoability first. Usage is only inferable from the verb itself.

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