Skip to main content
Glama

mouse_click

Click at screen coordinates with optional window-title-based guard to verify target identity. Supports double-click and triple-click for line selection.

Instructions

Click at screen coordinates. Normally pass windowTitle so the server auto-guards the click (verifies target identity, foreground, coordinate is inside the target rect) and returns post.perception without a confirmation screenshot. origin+scale from dotByDot=true screenshots are converted to screen coords before guarding. doubleClick:true for double-click; tripleClick:true for triple-click (selects a full line of text). Prefer click_element (UIA) for native apps, prefer browser_click for Chrome. Examples: mouse_click({windowTitle:'Notepad', x:200, y:150}) // guarded — post.perception.status='ok'. mouse_click({x:100, y:100}) // unguarded — post.perception.status='unguarded'. If a guard failure returns a suggestedFix, pass its fixId to approve the fix: mouse_click({fixId:'fix-...'}) // one-shot, expires in 15s. lensId is optional and only for advanced pinned-target workflows; omit it for normal use. Caveats: origin+scale are meaningful ONLY with dotByDot=true screenshot responses. hints.verifyDelivery:{status:'delivered'|'focus_only'|'unverifiable', reason} reports the post-click observation in 3 values (focused-element shift, window-foreground change, or no signal). Win11 foreground refusal during the homing path (UIPI cross-elevation / admin-only target / call from a background process or service) returns code:'ForegroundRestricted' ok:false rather than landing the click on the wrong window — recover by switching to a tool that accepts windowTitle directly (click_element / desktop_act) — browser_* tools target by tabId/selector, not windowTitle. MouseClickNotDelivered is reserved-only (false-positive risk is too high to emit a typed code), so degradation is expressed via the 'unverifiable' status, not a separate error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xYesX coordinate. Screen-absolute by default. When 'origin' is provided, treated as image-local (pixel position within the screenshot).
yYesY coordinate. Screen-absolute by default. When 'origin' is provided, treated as image-local.
originNoWhen set, (x,y) are image-local coords from a screenshot. Server converts to screen coords: screen_x = origin.x + x / (scale ?? 1), screen_y = origin.y + y / (scale ?? 1). Copy origin values directly from the screenshot response text. This eliminates manual coord math and prevents out-of-window clicks.
scaleNoScale factor from screenshot response (only when dotByDotMaxDimension caused a resize). Omit if the screenshot was 1:1. Only used when 'origin' is also provided.
buttonNoMouse button to clickleft
doubleClickNoWhether to double-click
tripleClickNoWhether to triple-click (select a line of text). Takes precedence over doubleClick when both are true.
narrateNoNarration level. rich includes UIA or browser state diff when supported.minimal
speedNoCursor movement speed in px/sec. 0 = instant.
homingNoEnable homing correction if the target window moved.
windowTitleNoPartial title of the target window.
elementNameNoName or label of the UI element.
elementIdNoAutomationId of the UI element.
hwndNoDirect window handle ID (takes precedence over windowTitle). Obtain from get_windows response (hwnd field). String type to avoid 64-bit precision issues.
forceFocusNoBypass Windows foreground-stealing protection before focusing.
trackFocusNoDetect if focus was stolen after the action.
settleMsNoMilliseconds to wait before checking post-action state.
verifyDeliveryYesParameter 'verifyDeliveryParam' from the Windows server schema.
lensIdNoOptional perception lens ID for advanced pinned-target workflows. When provided, guards are evaluated before clicking (safe.clickCoordinates, target.identityStable) and a perception envelope is attached to post.perception in the response. For normal use, omit lensId and pass windowTitle directly — Auto Perception handles tracking.
fixIdNoOne-shot fix approval ID. If a previous mouse_click returned a suggestedFix, pass that fixId here to approve it. The server revalidates the fix and executes with corrected args. fixId expires in 15 seconds and can only be used once.
includeNoOptional response-shape opt-in. `['envelope']` returns the self-documenting envelope (`_version` / `data` / `as_of` / `confidence`). `['raw']` forces raw shape (overrides DESKTOP_TOUCH_ENVELOPE=1 server default). Default behaviour is raw shape (compat with existing clients).
Behavior5/5

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

No annotations provided, but the description fully discloses guard behavior, coordinate conversion, post-click observation via hints.verifyDelivery, error handling (ForegroundRestricted vs unverifiable), and that MouseClickNotDelivered is reserved-only.

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 description is thorough and well-structured, starting with core purpose then detailing guarding, examples, and edge cases. It could be slightly more concise, but every sentence adds necessary context.

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?

Despite no output schema and 21 parameters, the description covers return statuses (post.perception.status, suggestedFix, verifyDelivery values), caveats (Win11 foreground restriction, origin+scale only with dotByDot=true), and recovery strategies. Complete for an experienced agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds significant value beyond schema: origin+scale conversion formula, doubleClick vs tripleClick precedence, fixId expiration (15s), lensId advanced usage, and verifyDelivery status values.

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?

Description clearly states 'Click at screen coordinates.' with specific verb and resource, and distinguishes from siblings like click_element and browser_click by naming them explicitly.

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

Usage Guidelines5/5

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

Explicit guidance on when to use this tool vs alternatives: 'Prefer click_element (UIA) for native apps, prefer browser_click for Chrome.' Also explains guarded vs unguarded usage, fixId approval, and recovery from foreground restrictions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Harusame64/desktop-touch-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server