Skip to main content
Glama

search

Perform Google searches directly within the Steel MCP Server to find information, answer questions, or gather data using web navigation capabilities.

Instructions

Perform a Google search by navigating to https://www.google.com/search?q=encodedQuery using the provided query text.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe text to search for on Google

Implementation Reference

  • The handler function that implements the core logic of the 'search' tool: validates the query input, encodes it, navigates to the Google search URL using Puppeteer page.goto, and returns a success message.
    async function handleSearch(page: Page, args: any): Promise<CallToolResult> {
      const { query } = args;
      if (!query) {
        return {
          isError: true,
          content: [
            { type: "text", text: "Query parameter is required for search" },
          ],
        };
      }
      const encodedQuery = encodeURIComponent(query);
      const url = `https://www.google.com/search?q=${encodedQuery}`;
      await page.goto(url);
      return {
        isError: false,
        content: [{ type: "text", text: `Searched Google for "${query}"` }],
      };
    }
  • Defines the input schema for the 'search' tool, specifying an object with a required 'query' string property.
      inputSchema: {
        type: "object",
        properties: {
          query: {
            type: "string",
            description: "The text to search for on Google",
          },
        },
        required: ["query"],
      },
    },
  • src/index.ts:467-481 (registration)
    The 'search' tool definition object within the TOOLS array, which is returned by the ListToolsRequestHandler to register the tool with MCP clients.
    {
      name: "search",
      description:
        "Perform a Google search by navigating to https://www.google.com/search?q=encodedQuery using the provided query text.",
      inputSchema: {
        type: "object",
        properties: {
          query: {
            type: "string",
            description: "The text to search for on Google",
          },
        },
        required: ["query"],
      },
    },
  • src/index.ts:919-921 (registration)
    Registers the 'search' tool handler in the switch statement of the main handleToolCall dispatcher function.
    case "search":
      result = await handleSearch(page, args);
      break;
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It mentions navigating to a URL, implying a web interaction, but lacks details on permissions, rate limits, error handling, or what happens after navigation (e.g., page load, search results display). This leaves behavioral gaps for a tool that interacts with external services.

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 that directly explains the tool's function without unnecessary words. It's front-loaded with the core action and includes the URL for clarity, making it highly concise and well-structured.

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 no annotations, no output schema, and a tool that performs external web navigation, the description is incomplete. It doesn't cover behavioral aspects like what the tool returns (e.g., success status, page content), potential errors, or integration with sibling tools, leaving significant gaps for agent usage.

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%, with the parameter 'query' documented as 'The text to search for on Google'. The description adds that the query is encoded in the URL, providing slight context beyond the schema, but doesn't elaborate on encoding specifics or constraints. Baseline 3 is appropriate given high schema coverage.

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 performs a Google search by navigating to a specific URL with a query. It specifies the action ('perform a Google search') and resource ('Google'), but doesn't distinguish it from sibling tools like 'navigate' which might also handle URLs, making it clear but not fully differentiated.

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?

The description provides no guidance on when to use this tool versus alternatives like 'navigate' for general URL navigation or other siblings. It merely states what the tool does without context for selection among available tools.

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/steel-dev/steel-mcp-server'

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