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

Annotations already declare destructiveHint=true and idempotentHint=false, so the description does not need to re-argue that this is a mutation. It adds genuinely new behavior: the undo is partial and scoped, restoring only the original value while leaving subsequent edits in place, and it is limited to three named source tools. It stops short of saying what happens with a stale or invalid changeId.

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?

Three short sentences: what it does first, the partial-undo caveat second, parameter provenance last. Nothing is padded and the most important constraint is front-loaded.

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 single-parameter destructive tool with no output schema, this covers purpose, source of the id, and the key non-obvious semantic (later edits survive). The remaining gap is failure behavior — what the caller sees when a changeId is expired or unknown — which an agent would want before invoking a destructive operation.

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 the single change_id parameter, so the description must carry the meaning — and it does, by naming the exact tools and list_actions/recentChanges as the source of the value. That is more useful than a format description, though it does not specify whether the id is opaque or how long it remains valid.

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 opens with a specific verb and resource ("Reverses a change") and scopes it to the three producing tools (update_ai_profile, set_tracked_questions, approve_changes), which makes the operation concrete. It does not, however, contrast itself with the sibling dismiss_change, which an agent could plausibly confuse with undoing a change.

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 tells the agent where the required changeId originates (the results of the three named tools, or list_actions/recentChanges), which is direct usage guidance for the single required parameter. It also gives a partial exclusions signal — edits made after the change are untouched — but never states when to prefer dismiss_change or what to do if the change is no longer reversible.

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