Nutanix AIops

snapshot_delete

Destructive

Delete a VM snapshot in Nutanix Prism Central. Use dry_run=True to preview the destructive action before committing.

Instructions

[WRITE][risk=high] Delete a VM snapshot. Destructive — pass dry_run=True to preview.

Tagged risk=high (audit tier 'review'); NUTANIX_AUDIT_APPROVED_BY /
NUTANIX_AUDIT_RATIONALE optionally annotate who/why. Captures the
snapshot's prior name on the audit trail.

Args:
    vm_ext_id: VM extId as returned by vm_list.
    snapshot_ext_id: Snapshot extId as returned by snapshot_list.
    dry_run: If True, return what WOULD be deleted without deleting.
    target: Prism Central target name from config; omit for the default.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "vm_ext_id": "<vm_ext_id>",
      "snapshot_ext_id": "<snapshot_ext_id>"
    },
    "name": "snapshot_delete"
  }
}

Input Schema

Name	Required	Description	Default
`target`	No
`dry_run`	No
`vm_ext_id`	Yes
`snapshot_ext_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Jul 28, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well past the annotations: reveals the 'review' audit tier, the NUTANIX_AUDIT_APPROVED_BY / NUTANIX_AUDIT_RATIONALE env vars needed to annotate who/why, that the snapshot's prior name is captured on the audit trail, and that dry_run returns a preview rather than performing the delete. This is rich behavioral context an agent cannot get from readOnlyHint/destructiveHint alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with risk tag and one-line purpose, then a compact Args block. Every sentence carries information, though the audit-tier paragraph is dense and slightly heavy for a description whose core job is delete semantics.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A destructive mutation with no output schema and no annotations documenting the audit workflow — the description covers the safety path (dry_run), audit requirements, and deletion scope, which is what an agent needs to call it correctly. Return shape is only implied ('what WOULD be deleted'), a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description documents all four parameters and adds meaning: vm_ext_id comes from vm_list, snapshot_ext_id from snapshot_list, dry_run's exact semantics, and target's defaulting behavior. This fully compensates for the schema's lack of descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource: 'Delete a VM snapshot.' The [WRITE][risk=high] tag immediately separates it from read siblings like snapshot_list, and the destructive framing distinguishes it from snapshot_restore/snapshot_create.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States the preview path explicitly ('pass dry_run=True to preview') and gives operational context for the audit tier, which tells the agent when this call needs extra authorization. It does not contrast against alternatives like snapshot_restore, but the destructive framing implies the boundary.

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