Undo

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

Annotations already declare destructive/non-idempotent, but the description adds substantial value beyond them: the (Claude)-suffixed one-step-per-tool-call semantics, the macOS-only API limitation requiring a menu-item trigger, the explicit return object shape, and the caveat that undo reverts user/other-tool changes. This is rich behavioral disclosure.

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?

Front-loaded with the core action and scope, then builds out semantics; nearly every clause carries non-obvious information. It is denser and longer than the ideal, but there is little waste.

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 mutation tool with no output schema, the description supplies the return shape (performed, requested, undone, next), the dryRun preview behavior, and the cross-user side-effect warning, so an agent has everything needed to invoke it correctly.

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 coverage is 100%, so the baseline is 3, but the description adds real semantics: it clarifies that steps counts whole tool calls (not raw operations) and that dryRun reports what would be undone next. Only 'force' is left to the schema alone.

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 (Undos) and the precise resource/scope (last Archicad operation(s)), and anchors it to a familiar UI analog (Edit > Undo). It is trivially distinguishable from the sibling 'redo' and from all create/modify tools.

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 operating context: steps:1 reverts one whole tool call, dryRun reports without performing, and a warning that undo may also revert user/other-tool changes. It does not explicitly route the agent to 'redo' or state when NOT to use it, so it stops short of full when/when-not guidance.

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