Skip to main content
Glama

Get one job

get_job
Read-onlyIdempotent

One job's details, by its slug: every covered country it is open or probably open to, each with what the evidence says (outcome), what it stands on (basis), the reason when only probably open (a partly remote job's or a field role's condition among them), and the words; pay, and country by country when the post states it so; kind of work, level, employment type and hiring model where known; the skills and requirements the post names; whom it reports to; what else the post says when it says it (experience, visa sponsorship, travel, time in person, start date, deadline, equity, languages, clearance, benefits, hiring steps, tests); and its link. A probably-open country is uncertain and carries its reason; a verdict from the location line only is weaker evidence. The post's full text is not returned: the link leads to it.

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": {
      "slug": "<slug>"
    },
    "name": "get_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesThe job's slug, from search_jobs.

Output Schema

NameRequiredDescriptionDefault
payYesthe post's pay; when it is the range of only some countries, it names them in brackets; 'currency not stated': the amounts are as written, not US dollars
urlYes
kindYeskind of work, First Monday's category from the title (it can be off; the title is the employer's own)
slugYes
factsNowhat the post says beyond where and how, each only when it says it: Experience, Visa, Travel, In person, Starts, Apply by, Equity, Languages, Clearance, Benefits, Hiring, Tests, Reports to
titleYes
closedYesYYYY-MM-DD the post closed; null while open
postedYes
posterYes
remoteYestrue: fully remote as far as First Monday can tell; false: it doesn't say, or it is partly remote or a field role somewhere (see verdicts' condition)
skillsYes
companyYes
locationYeswhere the post says the job is, as a card shows it
pay_noteNoset when pay is null but the post mentions pay: no range was read from it, the post has it
verdictsYeseach covered country the job is open or probably open to, with what the evidence says and why
seniorityNothe role's level when known: intern, junior, mid, senior, staff, principal, lead, manager, director, executive
reports_toYes
hiring_modelNohow one is hired, when known: employee, eor (through an employer of record), contractor, client_placement
requirementsYes
pay_by_countryYes
employment_typesNowhen known: full_time, part_time, contract, internship, temporary, freelance

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / slug / pattern
      Previous value: -"^[a-z0-9][a-z0-9-]{2,199}$"New value: +"^[a-z0-9][a-z0-9-]{2,2047}$"
  2. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld=false, non-destructive), so the bar is lower, and the description still adds real context: the post's full text is NOT returned and the link leads to it, and a 'probably open' verdict from the location line alone is flagged as weaker evidence. That uncertainty semantics is information an agent cannot get from annotations.

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

Conciseness3/5

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

Purpose is front-loaded, but the bulk is a long semicolon-chained enumeration of return fields that largely restates what an output schema already provides. Dense and readable but heavier than needed for a one-parameter lookup.

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

Completeness4/5

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

For a simple single-parameter read tool with an output schema, the essential gaps are covered: what is returned at a high level, what is deliberately not returned (full text), and how to interpret uncertain country verdicts. Only the not-found/error behavior is unaddressed.

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% for the single slug parameter, including its pattern and a note that it comes from search_jobs, so the schema does the heavy lifting. The description adds nothing about the slug's format, provenance, or failure modes (e.g. what happens with an unknown slug).

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?

Opens with a specific verb+resource: 'One job's details, by its slug,' which plainly separates a single-record fetch from the sibling search_jobs. It never names search_jobs in prose (only the schema does), so sibling routing is implied rather than stated.

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 only implied: you need a slug, and the schema notes it comes from search_jobs. There is no explicit 'use this when you already have a slug, otherwise call search_jobs' statement and no when-not guidance.

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.