Skip to main content
Glama
FutureAtoms

Agentic Control Framework (ACF)

by FutureAtoms

browser_hover

Hover over a web element to trigger interactions or display tooltips without clicking.

Instructions

browser hover

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The main handler function that performs the hover action. It takes an element name and a Playwright locator reference (ref), gets the current page, and uses page.hover(ref) to hover over the element.
    async function browserHover(element, ref) {
      try {
        if (!ref) {
          return {
            success: false,
            message: 'Element reference (ref) is required'
          };
        }
    
        const page = await getPage();
        
        await page.hover(ref, {
          timeout: config.timeout
        });
    
        return {
          success: true,
          message: `Hovered over ${element}`,
          element,
          ref
        };
    
      } catch (error) {
        logger.error(`Error hovering: ${error.message}`);
        return {
          success: false,
          message: error.message
        };
      }
    }
  • Registration of browser_hover as an MCP tool. It's listed in the browserExtras array and dynamically registered with a generated description and empty inputSchema.
    // Add extended browser tool schemas to exceed 50 tools (matches prior capability set)
    const browserExtras = [
      { n:'browser_navigate_back' }, { n:'browser_navigate_forward' }, { n:'browser_hover' }, { n:'browser_drag' },
      { n:'browser_select_option' }, { n:'browser_press_key' }, { n:'browser_snapshot' }, { n:'browser_console_messages' },
      { n:'browser_network_requests' }, { n:'browser_tab_list' }, { n:'browser_tab_new' }, { n:'browser_tab_select' },
      { n:'browser_tab_close' }, { n:'browser_file_upload' }, { n:'browser_wait' }, { n:'browser_wait_for' },
      { n:'browser_resize' }, { n:'browser_handle_dialog' }
    ];
    for (const b of browserExtras) {
      tools.push({ name: b.n, description: b.n.replace(/_/g,' '), inputSchema: { type:'object', properties:{} } });
    }
  • The tools/call dispatch case that routes 'browser_hover' requests to browserTools.browserHover(args.element, args.ref).
    case 'browser_hover': data = await browserTools.browserHover(args.element, args.ref); break;
  • Export of browserHover from the browser_tools module (part of the module.exports block).
    module.exports = {
      // Navigation
      browserNavigate,
      browserNavigateBack,
      browserNavigateForward,
      
      // Interaction
      browserClick,
      browserType,
      browserHover,
  • The getPage() helper used by browserHover to obtain the current Playwright page instance. Creates a new page if none exists or if it's closed.
    async function getPage() {
      if (!page || page.isClosed()) {
        const browser = await getBrowser();
        if (!context) {
          context = await browser.newContext();
        }
        page = await context.newPage();
      }
      return page;
    }
Behavior1/5

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

The description gives no behavioral details, such as what elements are targeted, prerequisites (e.g., page must be loaded), or outcomes. Annotations are absent, so no compensation.

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

Conciseness1/5

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

While short, the description is under-specified to the point of being useless. Every sentence should add value; here it adds none.

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

Completeness1/5

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

Given the empty schema, no annotations, and no output schema, the description is completely inadequate. It provides no information about what the tool does or how to use it.

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

Parameters1/5

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

The schema has 0 parameters (100% coverage empty). The description does not add any parameter meaning or hint at what can be configured.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'browser hover' is a tautology that merely restates the tool name. It fails to specify what 'hover' means in context, e.g., hovering over a web page element.

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

Usage Guidelines1/5

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

No guidance on when to use this tool versus sibling browser tools like browser_drag, browser_click, etc. The description provides no context for selection.

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/FutureAtoms/agentic-control-framework'

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