{
  "id": 16886715,
  "title": "MCP tool cost: 20 job Actors on Apify, 2.1K to 32.7K tokens each",
  "url": "https://urgent.news/2026/10/28/mcp-tool-cost-20-job-actors-on-apify-2-1k-to-32-7k-tokens-each",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-28T11:00:14.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/kevinhall/mcp-tool-cost-20-job-actors-on-apify-21k-to-327k-tokens-each-1hm4"
  },
  "original_language": "en",
  "account": "An agent's cost before querying a job-search tool is significant. Twenty job-search Actors from Apify's Store were pinned to the hosted Apify MCP server, revealing varying token counts for tool definitions. The smallest tool definition was 2,139 tokens, while the largest was 32,737. The median token count was 3,829, with 32,136 of those belonging to one tool, which consisted solely of an output schema inferred by the server from Actor results. The author's own input schema, however, was much smaller at 406 tokens. Three of the twenty tools were created by the author, allowing for a check on their work. This investigation occurred on October 28, 2026, and involved a simple curl handshake that could be repeated on any Actor within a minute.",
  "summary": "Here is what an agent pays before it asks a job-search tool anything. I pinned 20 job-search Actors from the Apify Store, one at a time, on the hosted Apify MCP server and read what tools/list sends back. The smallest tool definition was 2,139 tokens. The median was 3,829. One was 32,737, and 32,136 of those tokens were an output schema the server had inferred from the Actor's results; the…",
  "key_points": [
    "Twenty Apify MCP Actors used for job search cost analysis",
    "Token counts range from 2,139 to 32,737 per tool definition",
    "Author's input schema is 406 tokens, median is 3,829"
  ],
  "editors_take": "Large tool definitions and inferred output schemas significantly increase the token overhead for agents, creating a substantial cost barrier when integrating complex job-search tools into automated workflows.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}