Undo a review change

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds the important scope fact that exactly one change is reverted, but says nothing about the resulting state (is the change discarded, can it be re-applied, does the review list shrink) or any permission requirements.

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 action front-loaded and the identifier source in parentheses; nothing is wasted. It is slightly compressed in a way that trades readability for brevity ("put back" instead of "revert").

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 two-parameter mutation with no output schema, the definition covers what to pass and where to get it, but leaves the post-condition of the undo unspecified. An agent calling it cannot predict the resulting review state, which is a meaningful gap for a state-changing 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?

Schema description coverage is 100%, so the schema already documents both parameters and the baseline is 3. The description adds only the provenance of changeId (get_optimizer review.changes) beyond the schema's "Review change id.", which is a marginal but real addition.

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 ("put back" = revert) and resource (one final-review change), and points at the source of the identifier (changeId from get_optimizer review.changes). An agent can distinguish it from optimizer_review and optimizer_reset, though the phrasing is colloquial rather than explicitly "revert/undo."

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 gives a useful precondition — you must first obtain changeId via get_optimizer review.changes — which implies the tool is used after reviewing changes. There is no explicit when-not guidance and no comparison against related tools such as optimizer_reset or optimizer_review.

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