Skip to main content
Glama
FutureAtoms

Agentic Control Framework (ACF)

by FutureAtoms

browser_select_option

Select an option from a dropdown menu in the browser. Use this tool to automate form filling and filter selections during web interactions.

Instructions

browser select option

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The actual implementation of browserSelectOption. Uses Playwright's page.selectOption() to select option(s) in a dropdown by element reference and values array.
    async function browserSelectOption(element, ref, values) {
      try {
        if (!ref || !values || !Array.isArray(values)) {
          return {
            success: false,
            message: 'Element reference (ref) and values array are required'
          };
        }
    
        const page = await getPage();
        
        await page.selectOption(ref, values, {
          timeout: config.timeout
        });
    
        return {
          success: true,
          message: `Selected ${values.length} option(s) in ${element}`,
          element,
          ref,
          values
        };
    
      } catch (error) {
        logger.error(`Error selecting option: ${error.message}`);
        return {
          success: false,
          message: error.message
        };
      }
    }
  • Registration of the browser_select_option tool in the MCP server's tool list, with a dynamically generated description.
    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 call in the MCP server that routes the 'browser_select_option' case to browserTools.browserSelectOption() with args.element, args.ref, and args.values.
    case 'browser_select_option': data = await browserTools.browserSelectOption(args.element, args.ref, args.values); break;
    case 'browser_press_key': data = await browserTools.browserPressKey(args.key); break;
  • Helper function getPage() used by browserSelectOption to get or create the current Playwright page instance.
    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?

With no annotations and a single-word description, the tool reveals nothing about side effects, permissions, or behavioral traits. The agent cannot infer whether this tool is deterministic, requires a specific state, or has constraints.

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 fails to be concise in a meaningful way; it is under-specified. Every sentence should contribute information, but here the single phrase adds no value beyond the tool 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 the complexity of the tool (likely related to browser automation) and the presence of many sibling browser tools, the description is wholly inadequate. It does not provide any context to differentiate it from similar tools or to understand what the tool does.

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

Parameters4/5

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

The input schema has zero parameters, so the description does not need to explain parameter meanings. A baseline score of 4 is appropriate because there are no parameters to document, and the description cannot add value beyond the schema.

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 select option' is a tautology that simply restates the tool name without specifying the verb or resource. It does not clarify what action is performed or what 'select option' refers to, making it useless for an agent to understand the tool's purpose.

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 on when or when not to use this tool compared to sibling tools like browser_navigate, browser_click, or browser_handle_dialog. The description lacks any context for appropriate usage scenarios.

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