Skip to main content
Glama
chrome-fast
by ventos312

click

Activate a page element by ref number or CSS selector, auto-scroll it into view, wait for any resulting navigation, and return the updated page content.

Instructions

Click an element by ref number (from get_page/navigate) or CSS selector. Scrolls it into view first and, if the click starts a navigation, waits for the new page. Returns the updated page content. For elements use fill_form instead.

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": {
      "selector": "<selector>"
    },
    "name": "click"
  }
}

Input Schema

NameRequiredDescriptionDefault
buttonNoMouse button (default: left)
selectorYesElement to click: a ref number from get_page/navigate (e.g. "3") or a CSS selector

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does so well: it discloses implicit scrolling into view, that it will block waiting for a navigation the click triggers, and that the updated page content is returned. It omits failure behavior, timeouts, and what a non-left button implies (e.g. right-click opening a context menu), which keeps it below 5.

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 sentences plus a routing caveat, front-loaded with the action and the two input modes before the behavioral details. Every clause carries information an agent needs; nothing is filler.

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?

The mandatory return-value gap is closed in prose ('Returns the updated page content') since there is no output schema, and the navigation-wait behavior explains the tool's latency profile. What remains missing is error/timeout handling and guidance for dynamic elements, which matters for a browser-interaction primitive.

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 both parameters are already documented, and the description essentially restates the selector semantics rather than adding format details or precedence rules. The 'button' parameter is not addressed at all in the description, so the baseline 3 applies.

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?

States a concrete verb and target ('Click an element'), names both accepted addressing modes (ref number from get_page/navigate or CSS selector), and explicitly separates itself from fill_form for <select> elements. An agent can distinguish this from siblings like type or evaluate without reading any schema.

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?

Gives clear operating context and one explicit exclusion ('For <select> elements use fill_form instead'), plus it tells the agent where ref numbers come from (get_page/navigate). It stops short of general when-not guidance such as what to do if the element is missing or when to prefer evaluate.

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