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

Annotations already mark destructiveHint=true, so the description adds value by explaining the mechanism (restoring captured snapshot) and the prerequisite (allowlisting). This goes beyond annotations, though it could be more detailed about consequences such as irreversibility or state changes.

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, front-loading the core action and limitation. Every word contributes to understanding, and there is no redundancy or extraneous detail.

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?

With an output schema present and annotations covering safety, the description covers the essential behavioral constraints (allowlisting, snapshots). It is slightly less complete in detailing failure scenarios or error states, but it provides sufficient context for the agent to use the tool correctly.

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 coverage is 100%, so the schema already describes both parameters (auditLogId and reason). The description does not add any additional semantic information about parameters beyond what is in the schema, so a baseline score 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 is to revert an audited action by restoring a before snapshot, and specifies the limitation to allowlisted target tables. This distinguishes it from other audit tools like get_audit_log (read-only) and list_audit_logs (listing).

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 provides clear context by stating the tool only works for allowlisted tables with full snapshots, implying when it should be used. However, it does not explicitly mention when not to use it or suggest alternative tools (e.g., restore_* tools for specific entities), leaving some guidance implicit.

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