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

Annotations already mark the tool as destructive and not read-only. The description adds value by explaining the mechanism (restoring a before snapshot) and the allowlist limitation, which is behavioral context beyond the annotation flags. No contradiction exists.

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 description is two concise sentences with no filler. The primary action is front-loaded, and the constraint is stated briefly, making every word purposeful.

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?

Given the tool's scope and the presence of annotations and output schema, the description covers the core purpose, mechanism, and a key constraint. It lacks details about failure modes or the meaning of 'allowlisted', but remains reasonably complete for its context.

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?

The input schema provides 100% description coverage with clear meanings for both parameters ('auditLogId' and 'reason'). The description does not add extra parameter-level detail, so the baseline of 3 is appropriate.

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 clearly states the action ('Revert an audited action') and the mechanism ('restoring the captured before snapshot'). This distinguishes it from sibling restore_* tools, which restore deleted entities rather than reverting audit actions. The allowlist constraint adds clear scope.

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 description gives a clear context for use (reverting audited actions) and an explicit constraint ('Only works for allowlisted target tables with full before/after audit snapshots'). However, it does not name alternatives or explicitly state when not to use it beyond that constraint.

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