Undo

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

Annotations already declare destructiveHint=true, so the low bar applies; the description still adds genuinely new behavior — that the revert spans all affected trees and that undone changes cannot be redone (irreversibility). It does not say what happens when no transaction exists or whether the revert is atomic.

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?

Three short sentences, front-loaded with the action and scope, then the scope caveat, then the irreversibility warning. Every sentence carries distinct information.

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 only needs to convey scope and risk, which it does. The remaining gap is failure behavior (no transaction to undo, or partial failure across trees), which an agent would want before invoking a destructive global operation.

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?

Zero parameters, so there is nothing to disambiguate and 4 is the baseline. The description correctly signals there are no targeting arguments by stressing the operation is inherently collection-wide.

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?

Specific verb ('Revert') plus a precisely scoped resource ('the last collection-wide transaction, including all affected trees'). It explicitly distinguishes itself from per-tree history, so an agent can tell what it does and at what blast radius without opening the schema.

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 'global history, not per-tree history' clause tells the agent the condition under which this tool is the right choice versus any tree-scoped operation. It stops short of naming an alternative or stating when not to call it (e.g. when there is no transaction to undo).

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