Skip to main content
Glama
primadonna-gpters

AgentSkills MCP Server

web_search

Perform real-time web searches to retrieve structured results with AI-generated summaries, supporting both English and Korean queries for comprehensive information gathering.

Instructions

Perform a real-time web search and get structured results with a summary. Returns top results with title, URL, snippet, and an AI-generated summary.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query
maxResultsNoMaximum number of results to return (default: 5)
languageNoLanguage for results: 'ko' (Korean) or 'en' (English). Default: koko

Implementation Reference

  • The handler logic for the 'web_search' tool, which extracts arguments and calls the external AgentSkills API.
    case "web_search": {
      const { query, maxResults = 5, language = "ko" } = args as {
        query: string;
        maxResults?: number;
        language?: string;
      };
    
      const result = await callApi("/api/skills/web-search", {
        query,
        maxResults,
        language,
      });
    
      return {
        content: [
          {
            type: "text",
            text: JSON.stringify(result, null, 2),
          },
        ],
      };
    }
  • The tool definition and schema registration for 'web_search' in the ListToolsRequestSchema handler.
    {
      name: "web_search",
      description:
        "Perform a real-time web search and get structured results with a summary. " +
        "Returns top results with title, URL, snippet, and an AI-generated summary.",
      inputSchema: {
        type: "object",
        properties: {
          query: {
            type: "string",
            description: "The search query",
          },
          maxResults: {
            type: "number",
            description: "Maximum number of results to return (default: 5)",
            default: 5,
          },
          language: {
            type: "string",
            description: "Language for results: 'ko' (Korean) or 'en' (English). Default: ko",
            enum: ["ko", "en"],
            default: "ko",
          },
        },
        required: ["query"],
      },
    },
Behavior4/5

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

No annotations provided, so description carries full burden. Discloses 'real-time' nature (fresh data), result structure ('title, URL, snippet'), and AI-generated summary feature. Missing rate limits, auth requirements, or caching behavior, but covers primary behavioral traits well.

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?

Two efficiently structured sentences with zero waste. First sentence front-loads action and value proposition ('Perform... and get structured results'). Second sentence details output format. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but description compensates by detailing return structure (title, URL, snippet, AI summary). 100% input schema coverage reduces documentation burden. Lacks error handling or rate limit disclosure, but complete for a standard search tool.

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 coverage is 100% with clear descriptions for all 3 parameters (query, maxResults, language including defaults). Description adds no parameter-specific semantics beyond the schema, which is acceptable given the complete schema documentation. Baseline 3 appropriate.

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

Purpose5/5

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

Clear specific verb ('Perform') + resource ('web search'). Distinguishes effectively from siblings 'business_data' (internal company data) and 'code_review' (code analysis) by specifying 'web' as the domain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the domain specificity ('web search' vs internal 'business' data), but lacks explicit guidance on when to choose this over 'business_data' for company information or 'code_review' for code-specific queries. No 'when not to use' or prerequisite guidance provided.

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/primadonna-gpters/agentskills-mcp'

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