Skip to main content
Glama

Get an occupation

get_occupation
Read-onlyIdempotent

Map a job title in the user's own words to the occupation JobJump files it under, and optionally describe that occupation. Use it when the user's wording is unusual, colloquial, English or gendered and you want the canonical German occupation name, the other titles that mean the same job, or links to JobJump's salary, job-search and CV-template pages for it; and when the user asks what the job involves, what it requires, or how to write a CV for it. Give the title in job_title; the server normalises German gendered forms.

The result names the occupation as JobJump stores it, the four-digit KldB 2010 group code where JobJump maps one, up to 30 sibling titles with the total count, and up to 3 common alternative names that currently have postings on JobJump. search_jobs already matches every sibling title when given any one of them, so you do not need to search each alias separately.

Pass include: ["profile"] for JobJump's occupation profile (description, FAQs, typical skills, requirements, benefits, tags) and include: ["cv_guidance"] for the advice from JobJump's CV template (tips, common mistakes, key sections, featured skills, FAQs and the template link). Ask only for what the user needs; both are editorial content about the occupation in general. The profile leaves out sentences and FAQs about pay; use get_salary_benchmark or get_tariff_pay for pay.

When the title cannot be matched, the result is a success with resolved: null and a note; ask the user for another wording. The tool returns no salary figures and no postings – call get_salary_benchmark or search_jobs for those, and get_tariff_pay for public-sector pay tables.

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": {
      "job_title": "<job_title>"
    },
    "name": "get_occupation"
  }
}

Input Schema

NameRequiredDescriptionDefault
includeNoExtra sections to add. Omit for the short result. 'profile' adds JobJump's occupation profile: description, FAQs, typical skills, requirements, benefits and tags, with pay figures and third-party statistics left out. 'cv_guidance' adds the advice from JobJump's CV template for the occupation: tips, common mistakes, key sections, featured skills and FAQs.
job_titleYesOccupation or job title in the user's own words, German or English. Gendered German forms are normalised, e.g. 'Erzieherin' resolves like 'Erzieher'.

Output Schema

NameRequiredDescriptionDefault
noteYes
profileNoPresent only when include asks for 'profile'; null when JobJump has no published profile for the occupation.
resolvedYes
provenanceYes
cv_guidanceNoPresent only when include asks for 'cv_guidance'; null when JobJump has no published CV template for the occupation.
disclaimersYes
matched_inputYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover safety (readOnlyHint, idempotentHint), and the description adds substantive behavior beyond them: an unmatched title returns a success with `resolved: null` plus a note, the profile deliberately omits pay sentences and FAQs, and no salary figures or postings are returned. The 'ask only for what the user needs; both are editorial content' note also frames cost/value of the optional sections.

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?

Front-loaded with purpose and use cases before the result shape, optional includes, and the unmatched-title path. It is long, and the pay-exclusion point is made twice (once about the profile, once about the tool overall), which is the only real waste in an otherwise dense statement.

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?

Even though an output schema exists, the description adds the parts an agent still needs: the default short result contents, the conditional expansion cost, the failure mode, and explicit routing to salary/job tools. Nothing needed to invoke it correctly or interpret a null result is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description goes further by giving concrete call syntax (`include: ["profile"]`, `include: ["cv_guidance"]`) and by explaining that gendered German forms are normalised server-side — behavior the schema only hints at. It does not add much on `job_title` length or format limits beyond the schema.

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: map a job title in the user's own words to the canonical occupation record JobJump files it under, with an optional profile expansion. It also names the non-obvious scope (colloquial/English/gendered German titles normalised), which distinguishes it from get_job, get_employer and search_jobs.

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 triggers are given (unusual wording, wanting canonical German name, sibling titles, or JobJump resource links; plus questions about what the job involves or requires), and the excluded cases are routed to named alternatives: get_salary_benchmark, get_tariff_pay and search_jobs. It even states that search_jobs covers all sibling titles, so per-alias searching is unnecessary.

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.

Resources