machine_reset

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

The description goes beyond annotations by disclosing that the user loses unsaved state, that confirm=False previews the blast radius (machine count and assigned users) without acting, and that the operation is audited. This adds rich context not visible in the annotations alone.

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 front-loaded with the critical warning, then explains preview/confirm behavior, followed by a compact Args section. Every sentence provides value; there is no redundancy.

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 tool with no output schema, the description covers the purpose, preview mechanism, side effects, and alternative tool. It gives enough context for an agent to safely invoke it, including the audit note and source of machine IDs.

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?

With zero schema description coverage, the description compensates fully: machine_ids are sourced from machine_list, confirm toggles preview vs. actual reset, and target comes from config.yaml with a default. Each parameter's semantics are meaningfully explained.

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: 'Hard-reset desktop machine(s)' with a specific verb and resource. It also differentiates from the sibling tool vmware-aiops for graceful reboots, giving distinct purpose.

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 explicitly explains when to use this tool (hard reset, losing unsaved state), how to preview with confirm=False, and when not to use it (graceful in-guest reboot should use vmware-aiops). This provides strong usage guidance.

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