Skip to main content
Glama

create_job_hunt

Define job search criteria to track and apply for positions matching your titles, locations, skills, salary, and other preferences.

Instructions

Create a new job hunt to start tracking and applying to jobs. A job hunt defines what jobs you want to find based on titles, locations, skills, salary, etc. You need at least one job hunt to use match_jobs or add_job_to_applications.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesA name for this job hunt (e.g., "Senior Engineer roles in SF")
configYesSearch filters configuration
autoModeNoEnable full autopilot mode (default: false). When enabled, jobs are automatically matched, scored against your resume using AI, and applied to if they meet your minMatchScore threshold. Resume customization (if enabled) is applied before each application. Each auto-apply consumes a credit.
dailyLimitNoMaximum jobs to auto-apply per day (default: 5, max: 100)
minMatchScoreNoMinimum match score for auto-apply (0-1). Jobs below this score will not be auto-applied. Default is 0.70 (70%) when not explicitly set.
customizeResumeNoEnable AI resume customization for applications (default: false)

Implementation Reference

  • The registration and handler implementation for the `create_job_hunt` MCP tool.
    server.tool(
      'create_job_hunt',
      'Create a new job hunt to start tracking and applying to jobs. A job hunt defines what jobs you want to find based on titles, locations, skills, salary, etc. You need at least one job hunt to use match_jobs or add_job_to_applications.',
      {
        name: z.string().describe('A name for this job hunt (e.g., "Senior Engineer roles in SF")'),
        config: z.object({
          titles: z.array(z.string()).describe('Job titles to match (required)'),
          locations: z.array(z.string()).optional().describe('Locations to match. Use plain city names without state abbreviations (e.g., "San Francisco" not "San Francisco, CA"). For states, use the full state name (e.g., "Texas"). Use "Remote" to match remote jobs worldwide without country restrictions.'),
          countries: z.array(z.string()).optional().describe('Country codes (e.g., ["US", "CA"])'),
          companies: z.array(z.string()).optional().describe('Companies to include'),
          excludedCompanies: z.array(z.string()).optional().describe('Companies to exclude'),
          skills: z.array(z.string()).optional().describe('Required skills'),
          remote: z.boolean().optional().describe('When true, only return remote jobs. When false or omitted, return all jobs (both remote and non-remote).'),
          baseSalaryMin: z.number().optional().describe('Minimum salary'),
          baseSalaryMax: z.number().optional().describe('Maximum salary'),
          expLevels: z.array(z.string()).optional().describe('Experience levels (e.g., ["SE" for Senior, "MI" for Mid-level, "EN" for Entry])'),
          industries: z.array(z.string()).optional().describe('Industries (use get_industries to see valid values)'),
          companySize: z.array(z.string()).optional().describe('Company sizes (e.g., ["xs" for 1-50, "s" for 50-200, "m" for 200-1K, "l" for 1K-5K, "xl" for 5K+])'),
          h1bSponsorship: z.boolean().optional().describe('H1B sponsorship required'),
          relevancy: z.enum(['HIGH', 'MEDIUM']).nullable().optional().describe('Search relevancy mode - HIGH for strict title/skills matching (recommended), MEDIUM for broader keyword-based results. Default is null (MEDIUM behavior).'),
          dateOffset: z.enum(['24H', '1D', '2D', '7D', '14D', '1M', '3M', '6M', '9M', '1Y']).nullable().optional().describe('Only match jobs posted within this time window (e.g., "7D" for last 7 days). Default is "7D".'),
          workArrangement: z.array(z.string()).optional().describe('Work arrangement filter (e.g., ["Full Time", "Part Time", "Contract", "Internship", "Freelance", "Temporary"]). Defaults to ["Full Time"] if not set.'),
          excludedKeywords: z.array(z.string()).optional().describe('Keywords to exclude from job results'),
          excludedTitles: z.array(z.string()).optional().describe('Job titles to exclude from results'),
        }).describe('Search filters configuration'),
        autoMode: z.boolean().optional().describe('Enable full autopilot mode (default: false). When enabled, jobs are automatically matched, scored against your resume using AI, and applied to if they meet your minMatchScore threshold. Resume customization (if enabled) is applied before each application. Each auto-apply consumes a credit.'),
        dailyLimit: z.number().optional().describe('Maximum jobs to auto-apply per day (default: 5, max: 100)'),
        minMatchScore: z.number().optional().describe('Minimum match score for auto-apply (0-1). Jobs below this score will not be auto-applied. Default is 0.70 (70%) when not explicitly set.'),
        customizeResume: z.boolean().optional().describe('Enable AI resume customization for applications (default: false)'),
      },
      async (args) => {
        if (!args.config || !args.config.titles) {
          throw new Error('config.titles is required');
        }
        const jobHunt = await client.createJobHunt({
          name: args.name,
          config: args.config as JobSearchFilters,
          autoMode: args.autoMode,
          dailyLimit: args.dailyLimit,
          minMatchScore: args.minMatchScore,
          customizeResume: args.customizeResume,
        });
        return { content: [{ type: 'text' as const, text: JSON.stringify({ message: 'Job hunt created successfully', jobHunt: formatJobHunt(jobHunt) }, null, 2) }] };
      }
    );
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions that a job hunt is needed for other operations, but doesn't describe what happens after creation (e.g., whether it's immediately active, how it's stored, if there are limits on concurrent hunts, or what the return value looks like). For a creation tool with zero annotation coverage, this leaves significant gaps in understanding the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately concise with two sentences. The first sentence states the purpose clearly, and the second provides important usage context. There's no wasted verbiage, and the information is front-loaded with the core functionality.

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 creation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what happens after creation, what data is returned, whether there are side effects (like credit consumption mentioned in the schema's autoMode parameter), or how the created hunt integrates with the system. The schema handles parameter documentation well, but the description should provide more behavioral context.

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 parameters thoroughly. The description adds minimal value beyond what's in the schema, only mentioning that a job hunt defines criteria 'based on titles, locations, skills, salary, etc.' This doesn't provide additional semantic context beyond the comprehensive schema descriptions.

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: 'Create a new job hunt to start tracking and applying to jobs.' It specifies the verb ('create') and resource ('job hunt'), and explains that a job hunt defines search criteria. However, it doesn't explicitly distinguish this from sibling tools like 'update_job_hunt' or 'list_job_hunts' beyond mentioning that it's needed for 'match_jobs' and 'add_job_to_applications'.

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool: 'You need at least one job hunt to use match_jobs or add_job_to_applications.' This establishes a prerequisite relationship with other tools. However, it doesn't explicitly state when NOT to use it (e.g., vs. updating an existing hunt) or name specific alternatives among siblings.

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/6figr-com/job-gpt-mcp-server'

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