Skip to main content
Glama
claude-proxmox-controller

claude-proxmox-controller

send_files

Copy files and folders from the user's computer into a running VM or container, preserving names, timestamps, and folder structure; existing items stay unless replace is true.

Instructions

Copy files and folders of the user's computer (whole paths) into a folder of a running VM or container — names and times kept, folders whole. Fast over the network when the guest can reach the computer, otherwise through Proxmox (about 1 MB/s). What is there already is not replaced unless replace is true. The user sees every path in the approval window.

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": {
      "host": "<host>",
      "vmid": "<vmid>",
      "paths": "<paths>",
      "folder": "<folder>",
      "reason": "<reason>"
    },
    "name": "send_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYesThe host's id, from list_hosts.
vmidYesThe guest's ID (VMID).
ownerNoLinux guests: the user (or user:group) the copied items are given to. Without it they get the folder's owner — root in /tmp, where then only root can remove them.
pathsYes
folderYesThe guest's folder it goes into.
reasonYesWhy you are doing this, in a sentence. The user sees it in the approval window and in the log.
replaceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Adds substantial behavior beyond annotations: existing items are not replaced unless replace is true, timestamps and names are preserved, folders are copied whole, and every path appears in the user's approval window. Annotations already declare the mutation/safety profile, so this is a genuine value-add; the one gap is that the description says nothing about what the call returns or how partial failures surface.

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 purpose, then overwrite semantics, then performance, then approval visibility — a sensible order with no filler sentences. It is dense with parentheticals and em-dash clauses, but each carries distinct information.

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 7-parameter mutating transfer tool with no output schema, it covers direction, overwrite policy, ownership consequences, speed, and approval visibility well. Missing only return-value or error behavior, which is a modest gap given no output schema exists.

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?

Schema coverage is 71%, and the description compensates for the two undocumented parameters: paths is clarified as whole paths with names and times kept, and replace is explained semantically ('what is there already is not replaced unless replace is true'). Ownership and approval behavior reinforce the schema's own owner/reason notes rather than adding much new.

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?

States a specific verb and resource with direction: copy files and folders from the user's computer into a folder of a running VM or container. The 'of the user's computer ... into a folder of a running VM' framing makes the direction unambiguous, which implicitly separates it from receive_files, though no sibling is named explicitly.

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?

Gives a real performance tradeoff that informs selection: fast when the guest can reach the computer, otherwise via Proxmox at about 1 MB/s. It never states when to use a different tool (e.g. the reverse-direction receive_files) or any prerequisites, so usage is implied rather than prescribed.

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