Skip to main content
Glama
google-jobs-scraper

google-jobs-scraper

start_job_search

Initiates a Google Jobs search and returns a run_id; pass it to get_job_results to fetch listings, salary data, descriptions, and apply links.

Instructions

Start a Google Jobs search and return a run_id immediately. Step 1 of 2: then call get_job_results(run_id) to get the listings (title, company, location, salary, posted date, full job description and the real apply URLs).

Starts the hosted Apify Actor "datalume/google-jobs-scraper" with your own Apify
account. Requires the APIFY_TOKEN environment variable. It is PAID per unique job
saved (current price: https://apify.com/datalume/google-jobs-scraper ); searches with
no results and blocked pages are not charged. Starting a search spends money even if
the results are never fetched, so start one only when the user wants job data. The
run stops at max_jobs and at max_total_charge_usd. Every query is searched in every
location; one search takes about a minute (19 Nov 2026: 59 s with "fast" coverage).

Args:
    queries: job titles, skills or companies, e.g. ["registered nurse"].
    locations: cities, regions or countries, e.g. ["Houston, TX"]. Empty = no location.
    country: 2-letter country Google searches from, e.g. "us", "gb", "de", "in".
    language: Google language code. Use the local language outside English-speaking countries.
    date_posted: "any", "today", "3days", "week" or "month".
    employment_type: "any", "fulltime", "parttime", "contract" or "internship" (English searches).
    remote_only: remote / work-from-home jobs only (English searches).
    coverage: requests per search: "fast" (3), "standard" (9) or "max" (13). More requests = more unique jobs and a longer run.
    max_jobs: stop after this many jobs in total. Keep small to control cost and response size.
    max_total_charge_usd: hard spending cap for this search, in USD.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "queries": "<queries>"
    },
    "name": "start_job_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
countryNous
queriesYes
coverageNofast
languageNoen
max_jobsNo
locationsNo
date_postedNoany
remote_onlyNo
employment_typeNoany
max_total_charge_usdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does it well: it discloses the APIFY_TOKEN environment variable requirement, that the hosted Actor runs under the user's own account, a PAY_PER_UNIQUE_JOB pricing model with a price URL, the fact that zero-result and blocked searches are not charged, the cost-incurring side effect, the run stopping conditions (max_jobs, max_total_charge_usd), and an expected runtime of about a minute. This is well beyond what any structured field conveys.

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 critical line — what it does and the run_id return — is front-loaded, and the operator warnings about cost come before the Args block. It runs a bit long and the Args section restates the schema, with mild repetition between 'Step 1 of 2' and the payload list, but nearly every sentence adds decision-relevant information.

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

Completeness5/5

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

For a 10-parameter, cost-incurring, two-step async tool with no annotations and no output schema, the description supplies everything needed to call it safely: auth requirement, pricing model, hard caps, expected runtime, the run_id contract, and the pointer to the retrieval step. The only nit is an unstated default for max_jobs and country, which the schema itself already carries.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for all 10 parameters, and it does: each arg is given meaning, examples ('registered nurse', 'Houston, TX', 'us'/'gb'/'de'/'in'), and allowed values for date_posted, employment_type, and coverage (with request counts 3/9/13 and the cost/length trade-off explained). It also clarifies the non-obvious semantics that empty locations means no location filter, that every query runs in every location, and that employment_type and remote_only only apply to English searches.

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?

Opens with a specific verb and resource plus a return value: 'Start a Google Jobs search and return a run_id immediately.' It also positions itself as 'Step 1 of 2' and names the follow-up sibling get_job_results, so the agent can distinguish it from the retrieval tool without inspecting either schema.

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

Usage Guidelines5/5

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

Explicit when-to-use: 'start one only when the user wants job data,' with an explicit warning that starting spends money even if results are never fetched. It also names the required follow-up call (get_job_results(run_id)) and lists exactly what that step returns, leaving no ambiguity about the two-step flow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools