revert_snapshot

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

With no annotations, the description carries full responsibility for disclosing behavioral traits. It clearly warns of data loss ('All changes since the snapshot was taken will be lost'), marks the operation as destructive, and explains the preview behavior when confirm is false. It does not detail post-revert VM state or permissions, but these are partly covered by the output schema and are less critical given the explicit warnings.

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 well-structured. It opens with the destructive warning, states the purpose, lists consequences and prerequisites, then presents arguments in a clean list. Every sentence adds value, with 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?

For a destructive operation with a confirm flag, the description covers the essential aspects: what the tool does, the risk, the prerequisite, and the confirm semantics. It has an output schema, so return values are documented elsewhere. It could mention the post-revert VM state or whether the VM must be started manually, but the current description is sufficiently complete for safe invocation.

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 schema has 0% description coverage, so the description must compensate. It briefly explains each parameter: vm_id as VM identifier, snapshot_id as snapshot identifier, and confirm as a gate that must be true to execute. It adds meaning beyond the schema by explaining the confirm behavior, though it could provide more detail on identifier formats or value constraints.

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 with a specific verb ('revert') and resource ('virtual machine to a previous snapshot'), and it distinguishes itself from sibling tools like list_snapshots, create_snapshot, and delete_snapshot by focusing on the revert operation. The DESTRUCTIVE label immediately conveys the tool's purpose and risk.

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?

It provides a clear prerequisite ('VM should be stopped before reverting') and explains the confirm flag's role (must be true to execute, returns a preview otherwise). It does not explicitly name alternative tools, but the context of sibling snapshot tools makes when-to-use clear. No exclusions beyond the stopping requirement.

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