Skip to main content
Glama

browser_click

Click an element or exact viewport coordinates using DOM events, with left, right, or middle buttons and double-click support.

Instructions

Click an element or exact viewport coordinates with DOM events. Supports left/right/middle buttons and double-click.

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": {
      "tabId": "<tabId>"
    },
    "name": "browser_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
refNoElement ref from the latest snapshot in this document.
tabIdYesTab id from browser_tabs.
expectNoPost-action condition. Default timeout is 1.2 seconds in visible pages and 3 seconds in hidden pages. A mismatch does not undo the action; inspect before retrying.
browserNoBrowser id from browser_list, or chrome/firefox when only one instance matches.
frameIdNoFrame id from browser_frames; defaults to top frame.
revisionNoReject if the DOM revision differs from the snapshot.
selectorNoCSS selector. Must identify exactly one element.
inputModeNoAuto uses trusted Chrome text insertion only in the active foreground tab; DOM otherwise. Pointer actions and keys always use DOM.auto
clickCountNo
documentIdNoReject the action if this snapshot document has changed.
mouseButtonNoleft

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

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. 'With DOM events' is a genuinely useful signal that clicks are synthetic and may be detected as untrusted, but the description says nothing about scroll-into-view behavior, what happens when the selector matches nothing, or whether the action waits for load. The safety-relevant caveats (revision/documentId staleness checks, mismatched expect not undoing the action) live only in the schema.

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?

Two tight sentences, front-loaded with the action and the two targeting modes. No filler or redundancy. It is efficient but arguably too short for a 13-parameter tool, so the concision comes partly at the cost of coverage.

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

Completeness2/5

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

For a 13-parameter tool with no annotations and no output schema, this description is thin. It omits the snapshot/ref workflow, the expect post-condition semantics, staleness rejection via revision/documentId, and the inputMode distinction between trusted and DOM insertion, leaving the agent to reconstruct the calling protocol from schema prose alone.

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 69% with 13 parameters, so the description must add some value and it does: 'left/right/middle buttons' maps to mouseButton and 'double-click' gives meaning to clickCount, which has no schema description at all. 'Exact viewport coordinates' also clarifies that x/y are viewport-relative, another undocumented pair. It adds nothing for ref, selector, expect, revision, or documentId.

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?

Specific verb plus two targeting modes: 'Click an element or exact viewport coordinates.' Distinguishable from browser_hover, browser_drag, and browser_press by the click action, and it names button and double-click support. It does not explicitly contrast itself with those siblings, which keeps it below a 5.

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 guidance on when to click an element ref versus raw x/y coordinates, no mention that a fresh snapshot/ref is a prerequisite, and no note on when to reach for browser_press, browser_drag, or browser_hover instead. The two targeting modes are listed but the choice between them is left entirely to inference.

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