Graphite: undo

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

Annotations already declare the safety profile (non-read-only, destructive, not idempotent, not open-world), and the description usefully adds behavioral detail those annotations cannot convey: the undo granularity ('inserts, style, transform, rename and delete are each one step'). It still omits failure behavior (e.g. no-op or error when history is empty) and undo-depth limits, keeping it out of 5 territory.

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 no filler; the parenthetical earns its place by defining what constitutes one undo step 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 tool with full schema coverage and an output schema that carries return values, the description covers the essential behavior. The one real gap is the absence of any linkage to the graphite_redo counterpart, which matters in a sibling set that includes 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, which is the baseline-4 case; there is no argument surface for the description to disambiguate. Scoring higher is unnecessary since the description correctly implies the tool acts on the active document implicitly.

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 a precise scope ('the most recent change in the active document'), which is far more informative than restating the name. It does not name or differentiate itself from the obvious sibling graphite_redo, 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 this is the recovery action after the listed mutations, but the description never says when to prefer undo over redo or any other sibling, nor what happens when there is nothing to undo. Adequate-but-underspecified.

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