undo

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

With no annotations, the description carries the full burden. It does disclose the important behavioral fact that undo can revert another client's/user's action, which affects side effects on shared project state, but says nothing about failure behavior (empty history), reversibility via redo, or whether one call reverts one step or a batch.

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 short sentence with the scope caveat in parentheses, front-loaded and free of filler. Every element earns its place.

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, no-annotation, no-output-schema mutation tool, the description conveys what it changes and whose changes are in scope. A brief note on empty-history behavior or the redo pairing would make it fully self-sufficient.

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?

Zero parameters, so there is nothing for the description to disambiguate; the baseline applies. The description correctly implies no targeting arguments are accepted, matching the empty schema.

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 (undo) and resource (the last step) plus a scope qualifier that matters in a multi-client session: it can revert anyone's step, not just this client's. It never names redo, so the boundary with its most obvious sibling is left implicit.

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?

Usage is only implied by the tool name; there is no explicit statement of when to call undo versus redo, get_history, or get_changes, and no note about what to do when the history is empty. The 'anyone's' clarification mildly informs usage (the agent need not track whose change it was) but does not route between alternatives.

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