undo

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

With no annotations, the description carries the full burden. It usefully discloses that undo granularity is per tool call and that native mode reaches hand-made edits, which is real behavioral value. However, it says nothing about failure behavior (e.g., when there is nothing left to undo), limits, or whether steps is honored in native mode, which are the remaining gaps.

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?

Two short sentences with zero waste. The core action and its step semantics come first, and the mode caveat follows – appropriately front-loaded.

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 simple two-parameter tool with no output schema or annotations, this is nearly complete: it defines the operation, the unit, and the mode switch. Only edge cases such as exhausted undo history and the steps/native interaction are left unstated.

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% (bare titles and defaults only), so the description must compensate. It explains the native flag's meaning explicitly and conveys steps semantics through 'one tool call is one step' and 'last edit(s)'. The only ambiguity is whether steps also applies when native=true.

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 and resource ('Undo your last edit(s)') and clarifies the unit of work ('each tool call is one step: pixels, layer changes, selection...'). It also distinguishes the non-native mode from the native Krita stack mode, though it never names the sibling redo as the counterpart.

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?

Gives clear context for when to set native=true: it walks Krita's own undo stack and also covers edits made by hand. That effectively tells the agent which mode to pick, but there is no explicit when-not guidance or mention of redo as the alternative operation.

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