Skip to main content
Glama

desktop_cursor_overlay_enable

Enable and configure a cursor overlay for the selected desktop session so agent clicks, pointer movement, and intent labels are visibly rendered.

Instructions

agent-desktop cursor-overlay enable: Enable and configure the cursor overlay for the selected session

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "desktop_cursor_overlay_enable"
  }
}

Input Schema

NameRequiredDescriptionDefault
bowNoPath curvature multiplier from 0 (straight) to 3 (default 1)
rimNoCursor outline colour as a hex value (default #111318)
fillNoCursor body colour as a hex value (default: the accent colour)
sizeNoCursor size multiplier from 0.5 to 4.0 (default 1.0)
imageNoDraw the cursor from a PNG file instead of the built-in arrow; scaled by --size
labelNoShow caller-authored intent text beside the cursor overlay
accentNoCursor, ripple and element highlight colour as a hex value (default #4299FF)
tremorNoHand tremor amplitude in points, 0 to 4 (default 1.1)
hotspotNoPoint in the image, in image points from its top-left, that marks the click position (default 0,0)
dwell_msNoPause on the target before the action runs, 0 to 300 (default 0)
max_wordsNoLimit the cursor overlay label to 1-12 words (default 6)
no_rippleNoDo not play the ripple when the agent clicks
overshootNoOvershoot past the target as a fraction, 0 to 0.15 (default 0.035)
travel_msNoCursor travel time range in ms, short to long moves (default 90,320)
motion_seedNoVary each move deterministically from this seed
multi_agentNoRequire agent IDs for desktop UI actions; use without --agent-id to configure the session
no_highlightNoDo not outline the element when the agent clicks
pointer_imageNoPNG shown instead while the cursor rests on a button, link or other pressable control
pointer_hotspotNoClick point in the pointer image, in image points from its top-left (default 0,0)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full disclosure burden. It says the tool enables and configures, but not whether the setting is session-scoped or global, whether it persists after the session ends, what happens to existing overlay settings when only some of the 19 options are passed, or whether a selected session is a prerequisite. For a state-mutating tool with zero annotation coverage, that is a significant gap.

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?

A single front-loaded sentence with no filler. The only minor waste is the 'agent-desktop cursor-overlay enable:' prefix, which restates the tool name rather than adding information.

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?

All 19 parameters are documented in the schema and there is no output schema to explain, so the structured data covers most of the surface. What is missing is the operational context an agent needs before invoking a configuration mutation: session prerequisites, persistence, and interaction with the disable sibling.

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 100%, so every one of the 19 options already carries its own meaning, range, and default. The description adds nothing beyond the generic word 'configure' — it does not group the appearance options (rim, fill, accent, image) versus the motion options (travel_ms, overshoot, tremor, dwell_ms) or explain how multi_agent interacts with the rest. Baseline 3 is appropriate.

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: 'Enable and configure the cursor overlay for the selected session'. That is clearly distinguishable from the sibling desktop_cursor_overlay_disable. It stops short of naming the sibling or spelling out the relationship, but the purpose itself is unambiguous.

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

Usage Guidelines2/5

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

No when-to-use or when-not-to-use guidance. The existence of desktop_cursor_overlay_disable implies the toggle pair, but the description never says to call this only after a session is selected, nor whether re-enabling an already-enabled overlay is safe or idempotent.

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