Skip to main content
Glama

browser_hover

Hover over web elements to trigger dropdowns, tooltips, or interactive menus using Selenium WebDriver for browser automation and testing.

Instructions

Hover over an element

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
byYesLocator strategy to find element
valueYesValue for the locator strategy
timeoutNoMaximum time to wait for element in milliseconds

Implementation Reference

  • Registers the 'browser_hover' MCP tool, including its description, input schema reference, and inline handler function that delegates to ActionService.
    server.tool(
      'browser_hover',
      'Hover over an element',
      { ...locatorSchema },
      async ({ by, value, timeout = 15000 }) => {
        try {
          const driver = stateManager.getDriver();
          const actionService = new ActionService(driver);
          await actionService.hoverOverElement({ by, value, timeout });
          return {
            content: [{ type: 'text', text: 'Hovered over element' }],
          };
        } catch (e) {
          return {
            content: [
              {
                type: 'text',
                text: `Error hovering over element: ${(e as Error).message}`,
              },
            ],
          };
        }
      }
    );
  • Core handler logic for hovering over an element using Selenium WebDriver's action builder to move the mouse to the located element.
    async hoverOverElement(params: LocatorParams): Promise<void> {
      const locator = LocatorFactory.createLocator(params.by, params.value);
      const element = await this.driver.wait(until.elementLocated(locator), params.timeout || 15000);
      const actions = this.driver.actions({ bridge: true });
      await actions.move({ origin: element }).perform();
    }
  • Zod schema definition for element locator parameters (by, value, timeout), used as the input schema for the browser_hover tool.
    export const locatorSchema = {
      by: z
        .enum(['id', 'css', 'xpath', 'name', 'tag', 'class', 'link', 'partialLink'])
        .describe('Locator strategy to find element'),
      value: z.string().describe('Value for the locator strategy'),
      timeout: z.number().optional().describe('Maximum time to wait for element in milliseconds'),
    };
  • Calls registerActionTools in the aggregate tool registration function, which includes the browser_hover tool registration.
    registerActionTools(server, stateManager);
Behavior2/5

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

No annotations are provided, so the description carries full burden. 'Hover over an element' implies a non-destructive UI interaction, but it doesn't disclose behavioral traits like whether this triggers JavaScript events, changes element states, requires the element to be visible, or has side effects. For a browser automation tool with zero annotation coverage, this is insufficient behavioral context.

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?

The description is a single, efficient sentence with zero wasted words. It's appropriately sized for a simple action tool and front-loads the core functionality immediately. Every word earns its place in conveying the essential purpose.

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?

Given the tool's moderate complexity (browser interaction with 3 parameters), no annotations, and no output schema, the description is incomplete. It doesn't explain what happens after hovering, what the tool returns, error conditions, or how it integrates with other browser tools. For a tool in a rich sibling ecosystem, more context is needed for effective use.

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 the schema already documents all three parameters (by, value, timeout) with descriptions and enum values. The description adds no parameter information beyond what's in the schema. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no param info in description.

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

Purpose3/5

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

The description 'Hover over an element' clearly states the action (hover) and target (an element), making the purpose understandable. However, it lacks specificity about what 'hover' entails in this browser automation context and doesn't distinguish this tool from other element interaction tools like browser_click or browser_focus_element among the many sibling tools.

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 is provided about when to use this tool versus alternatives. The description doesn't mention use cases like triggering hover-dependent UI elements, testing hover states, or when other interactions (click, focus) might be more appropriate. With many sibling tools for element interaction, this omission leaves the agent without 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/pshivapr/selenium-mcp'

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