Skip to main content
Glama

desktop_key

Destructive

Press a key or a key combination on a desktop session: "enter", "esc", "tab", "ctrl+s", "alt+tab", "ctrl+shift+esc", "win+r", "f5", "pagedown"… Several separated by spaces are pressed one after another. Ctrl+Alt+Del can't be sent. 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": {
      "session_id": "<session_id>",
      "keys": "<keys>"
    },
    "name": "desktop_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysYese.g. "ctrl+s" or "enter"
session_idYesDesktop session id from desktop_list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag this as destructive, non-idempotent, open-world and not read-only, so the safety frame is covered. Beyond that, the description adds genuinely new behavior: multi-key sequences fire one after another, Ctrl+Alt+Del is blocked at the tool level, and the user can watch the session — all useful for planning. The stray sentence about screenshot coordinates describes a parameter this tool does not have, which muddies rather than clarifies behavior.

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?

The core action and its examples are front-loaded, and each sentence about sequencing, blocked combos, and secrets earns its place. The carousel of unrelated example keys is slightly padded, and the sentence "Coordinates are pixels of your last desktop_screenshot" has no referent in this tool's two parameters, so it is dead weight an agent must discard.

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?

With only two parameters, full schema coverage, and annotations covering the risk profile, the definition is nearly complete for calling the tool correctly, and no output schema exists so return values need no explanation. It leaves open how focus/target window is determined and what happens when a key combination is unsupported, but those are minor for a keystroke tool.

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 100%, so the 3 baseline applies, and the description exceeds it by explaining the encoding of the keys string: space-separated entries are interpreted as a sequential chord sequence rather than a literal string, which the schema's brief "e.g. ctrl+s or enter" does not convey. session_id is only restated as coming from desktop_list, matching the schema.

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 description gives a specific verb+resource ("Press a key or a key combination on a desktop session") and backs it with a concrete inventory of key names and combos, so an agent knows exactly what the tool does. It does not explicitly differentiate itself from the sibling desktop_type, leaving the agent to infer that free-text entry belongs there and discrete key presses belong here.

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?

Usage context is clear: use it for single keys or chorded combos, and space-separated entries are pressed in sequence. It also states a hard exclusion (Ctrl+Alt+Del cannot be sent) and a policy stop condition (never enter secrets; ask the user to type them) — strong guidance, though no sibling tool is named as an alternative.

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.