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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the mutation profile is known. The description goes beyond them by classifying which operation types are reversible and which are permanently non-recallable, a genuinely useful behavioral distinction. It does not, however, explain how a specific change is targeted.

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 core action and zero filler. Each sentence carries distinct information (scope, exclusions, where to read the result). The trailing reference to `say` is terse but functional.

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 output schema, the description usefully points to `say` as the location of a ready-to-read summary and covers reversibility boundaries. The one real omission is any explanation of the action_id parameter, which is left entirely to an undescribed schema field.

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?

Schema description coverage is 0% and the single optional parameter action_id is undocumented in both the schema and the description. Worse, the phrasing 'the last thing' implies no targeting input is needed at all, leaving the purpose of action_id opaque and potentially misleading.

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?

The description states a specific verb ('Undo') and scopes the resource ('the last thing that can be undone'), then enumerates the concrete operation types affected (edits, saves, moves, dismissals, preference changes). It is clearly distinguishable from read-oriented siblings like get_preferences or list_actions, though it never names restore_version, the closest alternative.

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?

It gives concrete when/when-not guidance: it lists what is undoable and explicitly states that a sent application or message cannot be recalled, which is exactly the boundary an agent needs. It stops short of naming a sibling alternative such as restore_version for the non-recallable cases.

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