Skip to main content
Glama

desktop_move

Destructive

Move the mouse pointer on a desktop session (e.g. to show a tooltip). 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>",
      "x": "<x>",
      "y": "<y>"
    },
    "name": "desktop_move"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYesHorizontal position, in pixels of the last desktop_screenshot
yYesVertical position, in pixels of the last desktop_screenshot
session_idYesDesktop session id from desktop_list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is largely covered. The description adds genuinely useful context beyond that — the session is user-visible in Termalin and coordinates are relative to the last desktop_screenshot. However, it frames the action as benign ('to show a tooltip') without explaining why it is flagged destructive (hover can trigger menus/state changes), leaving the agent with a softer risk picture than the annotations imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with the action and coordinate frame front-loaded, followed by the safety note. No redundancy or filler, and the most important constraint (coordinate frame) precedes the caveat.

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 3-required-parameter tool with no output schema and full annotation coverage, the description supplies the essentials: coordinate frame, session visibility, and a credential safety rule. Minor gaps remain around what happens with out-of-bounds coordinates or whether a prior screenshot is mandatory, but nothing critical to correct invocation is missing.

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% and both x/y already state 'pixels of the last desktop_screenshot', so the description only reinforces what the schema documents and adds no new syntax or boundary semantics. Baseline 3 applies when the schema does the heavy lifting; nothing extra is contributed for session_id beyond the schema's 'from desktop_list'.

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 opens with a specific verb+resource ('Move the mouse pointer on a desktop session') and adds a scoping example ('e.g. to show a tooltip') that implicitly separates it from desktop_click by signaling hover-only intent. It does not name desktop_click or any sibling explicitly, so the differentiation is inferred rather than stated.

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 tooltip example gives a concrete when-to-use signal, and the closing sentence implies a stop-and-ask policy when credentials are needed. There is no explicit statement of when NOT to use it (e.g. use desktop_click to actually activate a target) and no prerequisites beyond the coordinate reference.

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.