Skip to main content
Glama
vbr-write-mcp

vbr-write-mcp

by Aquatick

Restore Files

restore_files
Destructive

Restore backed-up files or folders to their original machine and path, or to another host, choosing to keep, overwrite, or restore permissions only.

Instructions

Restore files/folders from a file-level-restore mount.

original: back to the same machine and path. restore_type: Keep keeps existing files and writes the restored ones next to them under a RESTORED- name, Overwrite replaces existing files, PermissionOnly restores only permissions. another: to target_host / target_path. credentials_id: guest credentials if VBR cannot use the job's.

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": {
      "session_id": "<session_id>",
      "paths": "<paths>",
      "restore_type": "<restore_type>"
    },
    "name": "restore_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathsYes
session_idYes
destinationNooriginal
target_hostNodestination='another': FlrRestoreTargetHostModel - {'type': 'VMware'|'HyperV'|'CloudDirector'|'Agent', ...} (subtypes: VmwareFlrRestoreTargetHostModel etc., see describe_model).
target_pathNo
restore_typeYes
confirm_tokenNo
credentials_idNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description meaningfully adds to that: 'Overwrite' replaces existing files, 'Keep' writes a copy under a RESTORED- prefix, and 'PermissionOnly' touches only permissions. That is exactly the destructive-behavior detail an agent needs before committing. The gap is that confirm_token — apparently required for a destructive operation — is never mentioned, and there is no note on permissions or irreversibility.

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 action, then parameter notes, with no filler sentences. The telegraphic backtick style ('`another`: to `target_host` / `target_path`') is terse to the point of being slightly cryptic, which costs it a point.

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

Completeness3/5

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

An output schema exists, so return values need not be described, and the mode/enum semantics are covered. For a destructive 8-parameter tool, though, the undefined confirm_token, the unstated need for an existing mounted session, and the unexplained session_id/paths leave real gaps.

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

Parameters3/5

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

Schema description coverage is only 13%, so the description carries most of the burden. It does well on the ambiguous enums (destination, all three restore_type values) and on target_host/target_path and credentials_id, but leaves session_id, paths, and confirm_token entirely unexplained in both schema and description.

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

Purpose4/5

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

The first sentence gives a specific verb and resource ('Restore files/folders') plus the precondition ('from a file-level-restore mount'), which separates it from siblings like restore_hyperv_vm or restore_cloud_director_vm that restore whole VMs. It stops short of naming a sibling it must not be confused with, so it lands at 4 rather than 5.

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

Usage Guidelines3/5

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

The description explains the two destination modes and the three restore_type behaviors, which implies when each option applies. But it never states prerequisites explicitly (that a file-level-restore mount must already exist via start_file_level_restore/browse_file_level_restore) nor when to prefer this over those siblings, leaving the workflow to inference.

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