Skip to main content
Glama

desktop_open

Destructive

Open a remote desktop the user saved for AI in Termalin (see desktops in desktop_list). Signs in with the password the user saved — you never see it. Unless the user already allowed your app, they are asked to approve it (Telegram, phone or the Termalin cabinet); the call waits up to ~50 s, then says it's still waiting — call it again a minute later. Returns a session for the other desktop_* tools. Give a short reason the user will see. The user started this desktop session for you in Termalin and can watch it. Coordinates are pixels of your last desktop_screenshot. Never type passwords, keys or other secrets: when a sign-in or secret is needed, stop and ask the user to type it themselves.

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": {
      "desktop": "<desktop>"
    },
    "name": "desktop_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoDefault: the most you may do there
reasonNoWhy you need it, shown to the user (one sentence)
desktopYesId or label of a saved desktop, from desktop_list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations: saved-password sign-in the agent never sees, an approval prompt via Telegram/phone/cabinet, a bounded wait with a retry hint, a returned session handle, and the fact the user can watch the session. It also warns that coordinates refer to the last desktop_screenshot and forbids typing secrets.

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-loads the action and the identifier source, then layers the approval/wait behavior and safety rules. Dense but every sentence carries operational value; only the coordinate remark is slightly tangential.

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

Completeness5/5

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

No output schema exists, yet the description explains what is returned (a session for the other desktop_* tools) and covers the async approval path, which is the main failure mode an agent would hit.

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 coverage is 100%, so the schema already documents all three parameters. The description reinforces `reason` (shown to the user) and `desktop` (from desktop_list) but adds no new detail on `mode` beyond the schema's default note.

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 ("Open a remote desktop the user saved") and points to `desktops` in desktop_list for the identifier, so it is distinguishable from the desktop_* action siblings.

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?

Explains the approval flow, the ~50 s wait and the retry instruction, and says it returns a session for the other desktop_* tools. It does not explicitly state when not to open a desktop, but the context is clear enough to act on.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.