Skip to main content
Glama
automcp-app

Linkd MCP Server

by automcp-app

initiate_deep_research

Start comprehensive research by combining multiple search variations with optional contact enrichment to find LinkedIn profiles matching specific criteria.

Instructions

Initiate a deep research job that combines multiple search variations with optional email enrichment. Each result costs 1 credit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query to research
limitNoMaximum number of results to return (default: 30, max: 100)
schoolNoFilter results by school names
enrich_emailsNoWhether to enrich results with contact information (default: true)
acceptance_thresholdNoAcceptance score threshold (0-100) for a match (default: 60)

Implementation Reference

  • The async handler function that executes the tool logic: constructs a request to the deep research API endpoint, handles parameters with defaults and bounds checking, makes the POST request using makeLinkdRequest, parses response, throws error if failed, and returns formatted content.
    export const initiateDeepResearchTool = async ({
      query,
      limit = 30,
      school,
      enrich_emails = true,
      acceptance_threshold = 60,
    }: InitiateDeepResearchParams) => {
      const apiUrl = new URL("https://search.linkd.inc/api/search/deep_research");
      const body = {
        query,
        limit: Math.min(limit, 100),
        school,
        enrich_emails,
        acceptance_threshold: Math.max(0, Math.min(100, acceptance_threshold)),
      };
    
      const response = await makeLinkdRequest(apiUrl.toString(), {
        method: "POST",
        headers: {
          "Content-Type": "application/json",
        },
        body: JSON.stringify(body),
      });
    
      const responseData = await response.json();
    
      if (responseData.error) {
        throw new Error(
          `Failed to initiate deep research: ${JSON.stringify(responseData.error)}`
        );
      }
    
      return {
        content: [
          {
            type: "text" as const,
            text: `deep research job initiated: ${JSON.stringify(responseData, null, 2)}`
          }
        ]
      };
    };
  • Zod schema defining the input parameters for the tool, including descriptions, defaults, and constraints.
    export const initiateDeepResearchSchema = {
      query: z.string().describe("The search query to research"),
      limit: z.number().max(100).default(30).describe("Maximum number of results to return (default: 30, max: 100)"),
      school: z.array(z.string()).optional().describe("Filter results by school names"),
      enrich_emails: z.boolean().default(true).describe("Whether to enrich results with contact information (default: true)"),
      acceptance_threshold: z.number().min(0).max(100).default(60).describe("Acceptance score threshold (0-100) for a match (default: 60)"),
    };
  • Registration of the 'initiate_deep_research' tool with the MCP server using server.tool().
    server.tool(
      initiateDeepResearchName,
      initiateDeepResearchDescription,
      initiateDeepResearchSchema,
      initiateDeepResearchTool
    );
Behavior3/5

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 adds some context: it mentions that 'Each result costs 1 credit' (cost implication) and that it initiates a 'job' (asynchronous operation). However, it doesn't describe what happens after initiation (e.g., how to check status, expected response format, or error handling), which is critical for a tool named 'initiate' with siblings like 'check_deep_research_status'.

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 extremely concise and front-loaded: two sentences that directly state the tool's function and cost implication. Every word earns its place with zero waste or redundancy, making it easy for an agent to parse quickly.

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

Completeness3/5

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

Given the tool's complexity (initiating a research job with cost implications), lack of annotations, and no output schema, the description is incomplete. It doesn't explain the asynchronous nature (despite a sibling tool for checking status), what 'deep research' entails operationally, or what the agent should expect after invocation. The cost warning is helpful but insufficient for full contextual understanding.

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%, so the schema already documents all 5 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema (e.g., it doesn't explain how 'query' relates to 'search variations' or what 'enrich_emails' entails). Baseline 3 is appropriate when the schema does the heavy lifting.

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's purpose: 'Initiate a deep research job that combines multiple search variations with optional email enrichment.' It specifies the verb ('initiate'), resource ('deep research job'), and key features (search variations, email enrichment). However, it doesn't explicitly differentiate from sibling tools like 'search_for_companies' or 'search_for_users' beyond mentioning 'deep research'.

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. It mentions 'deep research' but doesn't explain how this differs from simpler search tools in the sibling list. There's no mention of prerequisites, use cases, or exclusions, leaving the agent to guess when this tool is 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/automcp-app/linkd-mcp'

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