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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the undo is a swap rather than a stack pop (calling again redoes), it is strictly one step, and it may silently be unavailable ('only when Cesure had room to keep that score').

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?

The action is front-loaded in the first clause and every element (scope, redo behavior, one-step limit, availability caveat) earns its place. It is a dense single sentence with an interrupting parenthetical, which is slightly harder to scan than it needs to be.

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?

An output schema exists, so return values need no explanation, and the one parameter is fully documented. The description supplies the irreversibility/redo model and the preconditions, which is close to complete for a single-step undo tool.

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?

With a single parameter at 100% schema description coverage, the schema already defines 'draft' as the id from a previous tool. The description refers to 'the draft' but adds no format, source, or validation detail beyond what the schema states, so the baseline 3 applies.

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 gives a precise verb and resource — restoring the draft's previous score state — and explicitly scopes what a 'last change' can be (edit_measures, transpose, refinger, or an undo), which separates it from those sibling tools without opening a schema.

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 states the operative conditions clearly: it applies after one of the four listed mutations and undoes exactly one step. There is no competing 'undo'-style sibling to redirect the agent to, so no explicit when-not clause is needed, but there is also no general guidance on what to do if more history is needed.

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