rollback_preview

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

Annotations already declare readOnlyHint=true, and the description reinforces that by stating 'without executing it' and 'preview'. It further explains what the preview shows ('which operations would be undone'), adding context beyond annotations. No contradiction.

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 extremely concise, with only a few sentences. It front-loads the core purpose, then explains the preview behavior, then gives parameter info. No wasted words.

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 simplicity (1 param, no nested objects) and presence of output schema, the description is complete. It explains the return format ('JSON string with preview') and the parameter, leaving no critical gaps.

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 0%, so description must compensate. The description explains the 'target' parameter as 'ISO timestamp or relative expression' and gives an example, adding significant meaning beyond the schema's type-only definition. However, it could provide more examples or constraints (like format).

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 it previews a rollback without executing it, using specific verbs and resource. It distinguishes from 'rollback' by explicitly being a preview, and from other siblings like 'rollback_history' or 'rollback_to_checkpoint' by focusing on a dry-run before execution.

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 explicitly says 'Always use this before an actual rollback', providing clear when-to-use guidance and implicitly when-not-to-use (not for executing rollback). No mention of alternatives, but the purpose is so specific that it's sufficient.

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