Skip to main content
Glama

Ats Detect

ats_detect
Read-onlyIdempotent

Detect which applicant-tracking system (ATS) a company publishes its public job board on, and its board token. Reads the company's careers page (or a given careers_url) for a Greenhouse/Lever/Ashby/SmartRecruiters/Recruitee/BambooHR/Workday/Workable/Teamtailor/Personio/Jobvite/Breezy/Pinpoint/Rippling/iCIMS link; falls back to slug-probing the domain name against each board API that supports it. Does not read any private/Harvest-key ATS data, only what a public job board already exposes. Discoveries persist so repeat lookups for the same domain are instant.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "domain": "ramp.com"
    },
    "name": "ats_detect"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainNoCompany domain, e.g. "airbnb.com" (no scheme, no path).
careers_urlNoA specific careers-page URL to scan instead of guessing one from domain, e.g. "https://www.airbnb.com/careers".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "domain": "ramp.com"
      -  }
      -]New value: +[
      +  {
      +    "domain": "ramp.com"
      +  },
      +  {
      +    "careers_url": "https://career.teamtailor.com/jobs"
      +  }
      +]
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent and open-world safety, but the description adds real non-obvious traits: a two-stage resolution strategy (careers-page scan, then slug-probing against board APIs) and persistent caching that makes repeat lookups instant. The data-access boundary ('does not read any private/Harvest-key ATS data') is also useful. It omits failure behavior when no ATS is detected.

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?

Two sentences, front-loaded with the core purpose before the resolution mechanics. The long enumeration of fifteen ATS vendors is somewhat bulky, but it usefully bounds what counts as a positive result.

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 two-optional-parameter read-only lookup with no output schema, the definition supplies the return values (ATS name and board token), the resolution fallback, the caching behavior, and the privacy boundary. An agent has enough to invoke it correctly for either input mode.

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% and both parameters are already documented, so the baseline is 3. The description does add the relational semantic that careers_url is used 'instead of guessing one from domain', which the schema alone does not convey, but it does not address the fact that zero parameters are required.

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?

States a specific verb and resource: detect which applicant-tracking system a company publishes its public job board on, plus the board token. This is clearly distinct from the listing siblings such as ats_company_jobs and ats_jobs, which imply job retrieval rather than ATS identification.

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 rather than stated: it is clearly the discovery step that precedes job fetching, and the careers_url parameter is framed as an override for guessing. However, no sibling is named, no explicit when-not-to-use condition is given, and the agent must infer that this should be called first for an unknown domain.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.