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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and closed-world scope, so the safety profile is covered structurally. The description adds genuinely useful scope context — that the undone change may have originated from the site, not just this session — but says nothing about the version-conflict behavior implied by expectedVersion or what happens on repeated calls given non-idempotency.

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 the verb and target up front, plus a docs link; no filler. Slightly compact given the undocumented parameters, but nothing is wasted.

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 two required, fully undocumented parameters and no output schema, the description omits precondition/failure behavior and return semantics. The only substantive detail added is the cross-context scope of the undo, leaving an agent unable to call it confidently against a version guard.

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% for two required parameters, and the description mentions neither sessionId nor expectedVersion. expectedVersion in particular carries concurrency semantics (it likely guards against undoing the wrong revision) that the agent cannot infer from the bare 'integer' type, so the description fails to compensate for the coverage gap.

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 the last change to the draft list') and scopes it to the most recent change only, which distinguishes it from the sibling applyAssistantTool/reviseAssistantTool pair that make forward changes. It does not explicitly name a sibling or contrast with a redo/version-history tool, so it falls short of full differentiation.

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?

'The last change' implies a single-step, most-recent-only undo rather than an arbitrary rollback, and '(from here or from the site)' signals it spans changes made outside this session. However, there is no explicit guidance on when to prefer this over applyAssistantTool/reviseAssistantTool or on failure/precondition handling.

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