Skip to main content
Glama
vbr-write-mcp

vbr-write-mcp

by Aquatick

Restore Cloud Director Vm

restore_cloud_director_vm
Destructive

Restore a VMware Cloud Director VM from a backup restore point into its original vApp, replacing the existing VM, or into a customized vApp with a new name and network/storage mapping.

Instructions

Full restore of a VMware Cloud Director VM from a restore point of a Cloud Director backup job.

OriginalLocation restores the VM into its original vApp, replacing the existing VM if it is still there. Customized restores it into vapp under new_name (required, keeps the original untouched), optionally with network mapping and datastore/storage policy. Inventory objects (vApp, networks, datastores) come from vbr-mcp browse_inventory on the Cloud Director server. proxy_ids pins backup proxies (default: automatic). Returns a restore session.

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": {
      "restore_point_id": "<restore_point_id>",
      "mode": "<mode>"
    },
    "name": "restore_cloud_director_vm"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
vappNoCustomized: target vApp, the inventory object exactly as browse_inventory returns it.
reasonNo
networkNoCustomized: RestoreTargetNetworkSpec {'networks': [{'sourceNetwork': obj, 'targetNetwork': obj}], 'disconnected': bool}.
new_nameNo
power_upNo
datastoreNoCustomized: {'datastore': obj, 'storagePolicy': obj} (CloudDirectorRestoreTargetDatastoreSpec).
proxy_idsNo
confirm_tokenNo
secure_restoreNoOptional SecureRestoreSpec: {'antivirusScanEnabled': bool, 'yaraScanEnabled': bool, 'yaraRule': str, 'virusDetectionAction': 'AbortRecovery'|'DisableNetwork'|'Ignore', 'entireVolumeScanEnabled': bool}.
restore_point_idYes
restore_vsphere_vm_tagsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, and the description earns its keep by specifying exactly what gets destroyed ('replacing the existing VM if it is still there') and what is safe (Customized keeps the original untouched). It also discloses the proxy default ('automatic') and that a restore session is returned. It does not explain `confirm_token` or any confirmation gating, which is a notable omission for a destructive operation.

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 the core purpose, then the mode split, then supporting details; no filler sentences. It is dense but every line carries operational meaning, aside from the slightly redundant 'Returns a restore session' given an output schema exists.

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?

For a 12-parameter destructive restore with an output schema, the definition covers the essential decisions: which mode, where the VM lands, how to source inventory objects, and proxy behavior. What it omits is the async workflow (the returned session presumably needs polling via get_session_result) and the meaning of `confirm_token`, both of which an agent would need in practice.

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

Parameters4/5

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

With only 33% schema description coverage across 12 parameters, the description compensates substantially by mapping parameters to modes — `new_name`/`vapp` are Customized-only, `vapp` must be the browse_inventory object verbatim, optional network mapping and datastore/storage policy apply only to Customized. It leaves `power_up`, `reason`, `confirm_token`, and `restore_vsphere_vm_tags` unexplained, so the coverage gap is only partly closed.

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?

States a specific verb and resource ('Full restore of a VMware Cloud Director VM') plus the source ('restore point of a Cloud Director backup job'), which cleanly separates it from restore_hyperv_vm and the file-level restore siblings. The two-mode breakdown makes the operation's scope unambiguous before an agent opens the schema.

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?

Gives explicit mode-selection guidance: 'OriginalLocation' replaces the existing VM in its original vApp, while 'Customized' targets `vapp` under `new_name` and keeps the original untouched. It also routes the agent to browse_inventory on the Cloud Director server for inventory objects. It stops short of naming when NOT to use this tool versus other restore siblings.

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