Undo

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

Annotations already declare destructiveHint=true, non-idempotent and not read-only, so the safety profile is covered. The description adds useful granularity beyond that - it undoes exactly one change, not a whole history - but says nothing about whether the change is recoverable via redo or what happens when there is nothing to undo.

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 zero wasted words, and the scope qualifier in parentheses is compact and informative.

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, the description supplies the one fact an agent needs (what unit of work is undone) and nothing more is required to call 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?

Zero parameters, so per the baseline the schema carries no semantics for the description to compensate for. No parameter detail is needed or expected here.

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 its target ('the last change'), and clarifies the granularity by naming what a 'change' can be (command, batch or gesture). This distinguishes it from redo, though the sibling inverse is not named 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?

Usage is implied by the verb and the 'last change' scoping, which signals a single-step undo rather than a history rollback. However, it never states when to reach for this instead of redo, nor any precondition (e.g. that an undoable action must exist), leaving guidance at the minimum viable level.

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