Skip to main content
Glama

browser_act

Automate browser interactions like clicking, form filling, content extraction, and navigation to streamline web-based workflows.

Instructions

Automate browser actions (click, fill, extract, navigate) ($0.005)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionsYesList of actions: {type, url/selector/text/script}

Implementation Reference

  • index.js:50-79 (handler)
    The generic tool handler function that fetches from the IteraTools API endpoint.
    async function callTool(endpoint, params) {
      const fetch = (await import('node-fetch')).default;
      const isGet = ['GET'].includes((TOOLS.find(t => t.endpoint === endpoint) || {}).method);
      
      const url = isGet 
        ? `${BASE_URL}${endpoint}?${new URLSearchParams(params)}`
        : `${BASE_URL}${endpoint}`;
      
      const res = await fetch(url, {
        method: isGet ? 'GET' : 'POST',
        headers: {
          'Content-Type': 'application/json',
          'Authorization': `Bearer ${API_KEY}`,
        },
        body: isGet ? undefined : JSON.stringify(params),
      });
      
      const text = await res.text();
      let data;
      try { data = JSON.parse(text); } catch { data = { raw: text }; }
      
      if (!res.ok) {
        if (res.status === 402) {
          throw new Error(`Insufficient credits. Add credits at https://iteratools.com. Cost: ${TOOLS.find(t=>t.endpoint===endpoint)?.price || 'see docs'}`);
        }
        throw new Error(`API error ${res.status}: ${text.substring(0, 200)}`);
      }
      
      return data;
    }
  • index.js:31-31 (registration)
    Registration of the browser_act tool in the TOOLS array, mapping it to the /browser/act endpoint.
    { name: 'browser_act', description: 'Automate browser actions (click, fill, extract, navigate)', inputSchema: { type: 'object', properties: { actions: { type: 'array', description: 'List of actions: {type, url/selector/text/script}', items: { type: 'object' } } }, required: ['actions'] }, endpoint: '/browser/act', price: '$0.005' },
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the cost ($0.005) but fails to disclose critical operational traits: whether sessions persist across calls, what happens if an action in the sequence fails, timeouts, or the return value format (since no output schema exists).

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, front-loaded sentence where every word serves a purpose. The cost annotation at the end is concise and material. There is no redundant or filler text.

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?

For a complex automation tool with no output schema, the description is materially incomplete. It omits what data is returned (HTML, JSON, success boolean?), whether the browser session is shared or isolated, and error handling behavior—all critical for an agent to use this tool effectively.

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?

While the schema has 100% description coverage and defines the actions array structure, the description adds crucial semantic meaning by mapping the generic 'type' field to concrete verbs (click, fill, extract, navigate). This helps the agent understand valid action values not explicitly enumerated in the schema.

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

Purpose4/5

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

The description clearly states the tool automates browser interactions and specifically enumerates the four supported action types (click, fill, extract, navigate). This distinguishes it from sibling tools like 'scrape' (passive extraction) and 'screenshot' (capture only). However, it could further clarify whether this operates on a live DOM or headless context.

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?

There is no guidance on when to use this tool versus alternatives like 'scrape' or 'code_execute'. It lists capabilities but does not specify prerequisites (e.g., when navigation is required before extraction) or exclusions (e.g., when simple HTTP fetching suffices).

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/fredpsantos33/itera-tools-mcp'

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