Skip to main content
Glama
FutureAtoms

Agentic Control Framework (ACF)

by FutureAtoms

browser_press_key

Simulate pressing a key in the browser to automate keyboard input for web interactions.

Instructions

browser press key

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The main handler function for 'browser_press_key'. It validates the 'key' argument, gets the current page via getPage(), calls page.keyboard.press(key) to simulate a keyboard press, and returns a success/error response.
    async function browserPressKey(key) {
      try {
        if (!key) {
          return {
            success: false,
            message: 'Key is required'
          };
        }
    
        const page = await getPage();
        
        await page.keyboard.press(key);
    
        return {
          success: true,
          message: `Pressed key: ${key}`,
          key
        };
    
      } catch (error) {
        logger.error(`Error pressing key: ${error.message}`);
        return {
          success: false,
          message: error.message
        };
      }
    }
  • Registration: 'browser_press_key' is added to the list of browser extra tools in the MCP server tool registry (line 129). A tool entry with name 'browser_press_key' and a basic description is pushed into the tools array.
    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:{} } });
  • Dispatch/case handler: In the MCP server's tool call dispatch, the case 'browser_press_key' delegates to browserTools.browserPressKey(args.key).
    case 'browser_press_key': data = await browserTools.browserPressKey(args.key); break;
  • Export: browserPressKey is exported from the browser_tools module (line 1139) so it can be imported by the MCP server.
    browserPressKey,
    
    // Capture
    browserTakeScreenshot,
    browserSnapshot,
    browserPdfSave,
Behavior1/5

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

With no annotations, the description bears full responsibility for disclosing behavior. It fails to mention what key is pressed, in which context, or any side effects. The tool is opaque, and the agent cannot infer safety or effects.

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

Conciseness2/5

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

The description is extremely short, but brevity without substance is under-specification, not conciseness. Every sentence should add value; this one adds none beyond the name.

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 zero annotations, no output schema, and no parameters, the description is wholly incomplete. An agent cannot determine how to invoke the tool or what to expect from it, rendering it nearly useless.

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

Parameters2/5

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

There are no parameters, so the schema carries no burden. However, the description should still clarify that the tool relies on implicit state (e.g., which key, where). It does not, leaving the agent guessing. Baseline 4 is reduced because no meaningful semantic context is added.

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 press key' is a tautology, simply restating the tool name without specifying any verb or resource. It does not differentiate the tool from sibling browser actions like 'browser_hover' or 'browser_select_option'.

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 guidelines are provided on when to use this tool versus alternatives. The description gives no context about prerequisites, typical use cases, or situations where a different tool would be more appropriate.

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