vm_rollback_plan

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

The description adds behavioral context beyond annotations: it rolls back in reverse order, skips irreversible steps with warnings, and marks itself as [WRITE]. This complements the destructiveHint=true annotation effectively.

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 concise and front-loaded with [WRITE] and core purpose. The Args section is necessary given 0% schema coverage, but it could be integrated more cleanly. Still, no wasted sentences.

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 rollback tool, it covers when to use, what it does (reverse order, skip irreversible), and parameters. Missing return value details, but no output schema exists. Overall sufficient for the 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?

Schema coverage is 0%, but the description explains both parameters: plan_id is 'the plan ID of the failed plan', and target is 'Optional vCenter/ESXi target name from config'. This adds meaning beyond the schema titles.

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 specifies the action ('rollback'), the resource ('executed steps of a failed plan'), and the order ('reverse order'). It distinguishes from sibling tools like vm_apply_plan and vm_create_plan by being specifically for rollback after failure.

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?

Explicit guidance is provided: call only after vm_apply_plan returns status='failed' and user confirms. It also warns that irreversible steps are skipped with a warning, which helps the agent decide when to invoke.

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