vm_rollback_plan

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds behavioral details: reverse order execution and skipping irreversible steps with warnings. This goes beyond annotations by clarifying what happens to destructive operations.

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 with no unnecessary words. It uses a clear structure: a one-line summary with [WRITE] prefix, a context/usage note, and an Args section. Every sentence adds value.

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?

The description covers when to call and parameter semantics but lacks information about tool output or return behavior. Since there is no output schema, the agent cannot infer what the tool returns upon success or failure, which is a notable gap for a post-failure rollback 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 0%, but the Args section provides meaningful descriptions for both parameters: plan_id is 'The plan ID of the failed plan' and target is 'Optional vCenter/ESXi target name from config.' This adds context that the schema alone did not provide.

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 tool performs rollback of executed steps from a failed plan in reverse order. It explicitly labels it as a write operation and distinguishes it from sibling tools like vm_apply_plan by specifying the exact post-failure context.

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 explicit when-to-use guidance: only after vm_apply_plan returns status='failed' and user confirmation. It also explains that irreversible steps are skipped with a warning, effectively telling the agent when not to expect full rollback.

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