Skip to main content
Glama

Search remote jobs open to a country

search_jobs
Read-onlyIdempotent

Remote jobs a person can do from where they live, by role, company, kind of work, pay or how recent: a search of First Monday's index of remote, English-language jobs for ones open to people living in one country, in firstmonday.ai's recommended order (fresh first, a company's further jobs, agencies and flagged companies lower) or with sort newest by date alone, 20 a page, up to 5 pages. Each result says whether it is open to people in that country and on what the verdict stands (basis: the post's own words, the employer's listing, or only the location line, which is weaker evidence) with the words; where it is and whether the post says fully remote; pay for that country (a range stated only for other countries is marked so: it is not pay for that country); kind of work, and level, employment type and hiring model where known; every other covered country it is open or probably open to; the posting date; who posts it when not the employer; a few skills; and the link to the job's page, where the person reads the post and applies. By default only jobs open there; with include_probably, also jobs only probably open (status probably_open, with a reason: only some regions, time zones, only the location names it, check the post, country from the listing (the job board files it under the country; the post doesn't say where one must live), what the post holds it on (it names other countries, moves the person or ties the job to another country, means the company's own sites, or names the country only as its clients'), or a partly remote job's or a field role's condition such as 'Field role · Midwest' or 'Remote or hybrid, by choice'): those are uncertain, and the post decides. A job is fully remote only when remote is true. Pay that says 'Up to' or 'From' is one side of the pay only, not an exact amount. Not in a result: a job's requirements, reporting line, pay country by country, each country's words, and what else the post says (experience, visa sponsorship, travel, time in person, benefits, hiring steps); a single job's details hold them.

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": {
      "country": "<country>"
    },
    "name": "search_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoKind of work, as the site names it: Engineering, Sales, Customer success, Data and AI, Operations, Finance, People and HR, Marketing, Product and design, Healthcare, Education, or another the catalog has since added.
pageNoPage of 20 results, 1 to 5.
sortNoOrder, as firstmonday.ai's lists offer it. recommended (default): fresh jobs first, a company's further jobs, agencies and flagged companies lower. newest: by posting date alone; jobs whose posting date is unknown come after the dated ones.
levelNoOnly jobs at this level as the job's title (or, rarely, its text) names it: intern; entry (junior, entry-level, graduate); mid; senior (Senior, Sr.); lead (Lead, Team Lead); staff (staff or principal); director (head of, director); executive (VP or C-level). Never worked out from years or pay. Most titles name no level and are left out by any value.
queryNoWords in the job title or the company's name, e.g. 'customer success' or 'GitLab'. Omit to list all.
equityNotrue: only jobs whose post offers equity: stock options, RSUs, shares or equity. An employee stock purchase plan alone (buying shares at a discount) doesn't count. Omit or false: every job.
countryYesWhere the person lives, as an ISO 3166-1 alpha-2 code (e.g. US, GB, DE); list_countries names them.
min_salaryNoMinimum yearly pay in US dollars, against the top of the stated range ('up to' pay by its top, 'from' pay by its floor). Only base pay stated per year or per month counts, other currencies at fixed exchange rates; hourly, daily and weekly rates, on-target (OTE) and total pay never match, though a result may show them. A range stated only for another country counts too: its pay says so. Leaves out jobs that state no pay, and pay whose currency the post doesn't state.
english_onlyNotrue: leave out jobs whose post requires a spoken language other than English (German, Spanish…); a language only preferred or 'a plus' doesn't count, and a post that names no language stays. Omit or false: every job.
fully_remoteNotrue: only jobs fully remote as far as First Monday can tell (their remote is true): none with a hybrid option, an office one must live near, regular time in person, or field work in some country; and jobs the person may do fully remote in this country by their own choice (remote or hybrid, the person's pick: such a job is probably_open with the reason 'Remote or hybrid, by choice', so it shows with include_probably, and its remote is false). Jobs First Monday hasn't read for it count by whether the post says remote. Omit or false: every job.
manages_peopleNotrue: only jobs whose post says the person manages people (direct reports, hiring and leading a team); a title alone doesn't count. Omit or false: every job.
employment_typeNoOnly jobs whose post says this kind of employment: full_time, part_time, contract (contract or freelance work), internship. A post may say several (part-time or full-time). Posts that say none (about 4 in 10) are left out by any value.
exclude_agenciesNotrue: only the employers' own jobs: none posted by a recruitment or staffing agency, and none whose post says the person is placed at a client (staffing, outsourcing) or that the poster recruits for another company. Omit or false: every job (agencies' sit lower in the recommended order).
include_probablyNoAlso return jobs only probably open to people in the country (status probably_open, with a reason). Default false: only jobs open there for sure.
posted_within_daysNoOnly jobs posted in the last N days, or, when the source gives no date, first seen by First Monday in them (their posted is null); never one already up when First Monday first read its source, whose date is unknown.
max_years_experienceNoOnly jobs whose post asks for at most this many years of experience: 2 or 5. A post's years are the strictest it states ('10+ years in SRE; 2+ years mentoring' asks 10; '3-5 years' asks 3; 'up to 2 years' alone asks 2), as First Monday read them. Posts that state no years (about 3 in 10) are left out: omit it unless the person asks about experience.

Output Schema

NameRequiredDescriptionDefault
moreYeswhether a next page exists (up to page 5)
pageYes
totalYesjobs that match, counted up to 100+
countryYesISO 3166-1 alpha-2, the country searched
relaxedNoonly when page 1 has no results: how many jobs the same search finds with one of its conditions changed, each only for a condition the search set. The words match as one phrase, in a job's title or its company's name
resultsYes
country_totalNoonly when page 1 has no results: the jobs open to people in the country searched, and apart those only probably open there, as list_countries counts them

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Adds substantial behavior beyond the read-only annotations: recommended ordering, 20-per-page pagination up to 5 pages, result fields, verdict basis, probably_open reasons, what counts as fully remote, pay caveats, and what is excluded from results. There is no contradiction with the annotations, and the disclosure is unusually rich.

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?

The opening front-loads the purpose well, but the description is a dense, run-on block with many clauses and could be organized more clearly. It is informative but not concise.

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 complex 16-parameter search tool with an output schema and detailed annotations, the description covers default behavior, result contents, uncertainty handling, pay caveats, pagination, and what must be retrieved from a single-job tool. Nothing essential for correct invocation appears missing.

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 description coverage is 100%, so the schema already documents the 16 parameters in detail. The description reinforces defaults and interactions such as include_probably and recommended sort, but it does not add much parameter-level meaning 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: searching First Monday's index of remote, English-language jobs open to people in one country. It also distinguishes the scope from sibling tools by noting that a single job's fuller details live elsewhere, and it names list_countries for country codes.

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

Usage Guidelines4/5

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

Gives clear usage context: default results are only jobs open in the country, while include_probably widens to probably_open jobs, and the description mentions list_countries for country codes and a single job's fuller details elsewhere. It does not explicitly say when to prefer get_job over search_jobs, but the alternatives are identifiable from context.

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.