vm_delete

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotence, so the safety profile is covered. The description adds real value beyond that: audit tier 'review', the NUTANIX_AUDIT_APPROVED_BY / NUTANIX_AUDIT_RATIONALE attribution variables, and the fact that prior name/power state is captured on the audit trail. It stops short of saying whether the delete is reversible or how child resources/snapshots are handled.

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?

Front-loaded with the risk/write tag, then the core action, then structured Args. The dry_run preview is stated twice (opening line and Args block), which is mild redundancy, but the block is compact and every section is scannable.

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 3-parameter destructive tool with no output schema, the description covers risk level, preview mechanism, audit attribution, and all parameters. It omits post-delete side effects (irreversibility, snapshot/protection-domain handling) and any required VM state, which an agent about to destroy a VM would benefit from knowing.

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%, so the description carries the full burden and does so: vm_ext_id is tied to vm_list output, dry_run is explained as a preview that returns what WOULD be deleted, and target is described as a Prism Central config name that defaults when omitted. Only formatting details (extId shape, valid target names) are left implicit.

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?

States a specific verb and resource ('Delete a VM') and immediately flags it as destructive, which cleanly separates it from siblings like vm_power_off, vm_update, or snapshot_delete. The [WRITE][risk=high] prefix gives an instant operation-class signal.

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 tells the agent to pass dry_run=True to preview first, which is actionable invocation guidance, but never states when this tool is the right choice versus alternatives such as vm_power_off or protection/undo workflows. No prerequisites (e.g., power state, protection domain removal) are mentioned.

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