undo_redo

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description does not contradict that. It adds genuinely useful context (batch mode has no inter-call history), but omits reversibility semantics, what happens when there is no history left to undo, and any permission/auth requirements.

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 the core action first and the mode caveat in parentheses. No filler, though the parenthetical is slightly compressed at the cost of clarity.

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 4-parameter mutation tool with no output schema and no annotations covering behavior, the description covers the core purpose and the live/batch distinction. It still leaves the 'steps' parameter behavior and no-history edge cases unaddressed, so it is adequate but not 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?

Schema description coverage is 50%: 'sprite' and 'backend' are documented in the schema while 'steps' and 'action' are not. The description alludes to steps being undoable/redoable but adds no detail on the steps count, defaults, or the undo/redo enum meaning, so it only partially compensates.

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 names a specific verb pair (undoes/redoes) and a specific resource (steps on a sprite), which is unambiguous and matches the tool name. No sibling tool competes for this function, so differentiation is implicit rather than stated.

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 one useful usage constraint – that batch processes have no history between calls, so undo/redo is effectively live-only. However, it doesn't state prerequisites, ordering considerations, or what to do in batch mode instead, leaving the guidance partial.

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