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

Annotations already declare destructiveHint=true, but the description specifies exactly what is destroyed — disk contents — plus a human-confirmation requirement and the permission scope (vms.action), which are genuinely additive. It does not say whether the machine keeps its id, IP, or SSH keys after redeploy, which is the remaining behavioral gap.

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?

Four short sentences, with the consequence (ERASES THE DISK) front-loaded in capitals ahead of the procedural rules. No sentence is filler.

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, irreversible operation with no output schema, the description covers data loss and confirmation but omits what state survives the reinstall (hostname, IPs, attached keys) and what ssh_keys/password_delivery do. Adequate to call safely, not complete.

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?

At 60% schema coverage, the description largely restates the schema's own wording for confirm_hostname rather than adding meaning. ssh_keys and password_delivery are undocumented in both the schema and the description, so the description does not compensate for the coverage gap.

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?

"ERASES THE DISK and redeploys another image" states a specific verb (reinstall/redeploy) and resource (the machine's disk) with the destructive effect front-loaded. An agent can tell it apart from create_vm and destroy_vm by the redeploy-with-data-loss framing, though no sibling is named explicitly.

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?

"Ask the user first" is an explicit interaction prerequisite, and the confirm_hostname rule gives a clear precondition for a successful call. It lacks any when-not/alternative guidance (e.g., versus destroy_vm + create_vm), which keeps it below a 5.

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