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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this mutates state. The description adds the useful detail of what can be undone (blocks, connections, deletions, parameter updates), but omits edge behavior: what happens when the AI history is empty, undo depth, and whether the action is recoverable via redo.

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 sentence with the core operation front-loaded and the parenthetical scope list appended concisely. No filler or redundancy.

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 no output schema and annotations covering the safety profile, the description covers the essentials. It stops short of explaining failure modes (empty history) or the relationship to redo, which would make it fully complete.

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 and the baseline of 4 applies. No parameter syntax or defaults are needed or missing.

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 (undoes) plus the exact resource (the last AI canvas modification) and enumerates the modification types covered (add block, connect, delete, update parameter). It is clearly the inverse of the sibling redo_last_ai_action, though it never names that sibling explicitly.

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?

No guidance on when to invoke this versus alternatives; redo_last_ai_action is the obvious sibling and is not mentioned. There is also no indication of prerequisites such as remaining AI history, which is essential for an undo tool.

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