Skip to main content
Glama

JobCrawls

by com.jobcrawls
OverviewDiscussionsAdmin

Search Finnish job listings

search_jobs
Read-onlyIdempotent

Search active job listings on JobCrawls, an aggregator of jobs in Finland. Use for questions like "find nurse jobs in Tampere", "onko Helsingissä avoimia etätyöpaikkoja ohjelmistokehittäjälle", or "finns det lediga jobb som sjukskötare i Åbo". The index covers jobs located in Finland plus remote roles open to Finland, and has no listings for other countries (jobs in Stockholm or Berlin are out of scope). Supports free-text queries plus facet filters (field, location, job type, seniority, skills, languages, industry, education, and more). Results, filter values and job text come back in the language of the query when locale is omitted; pass locale explicitly to override. Returns a scoped, paginated list, each with title, company, location, remoteness, salary range when known, and a direct link to the individual posting. list_job_filters returns the available filter values, and get_job_details returns the full description of a result. Some results are sourced from Job Market Finland (Työmarkkinatori); those results have isTyomarkkinatori:true and a dataSource attribution string, which MUST be shown alongside that posting wherever you present it, per Job Market Finland's terms of use.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number, starting at 1. Default: 1.
sortNoOrdering: relevance (default), date (newest first), or salary (highest minimum first).
limitNoResults per page (1–20). Default: 10.
queryNoFree-text search across job title, description, skills, company, and location. Example: "senior software engineer". Leave empty to browse the newest listings.
localeNoSet this to the language of the user's message (fi for Finnish, sv for Swedish, en for English or any other language), even when the job titles or place names in it are English. Language index to search: en = English, fi = Finnish, sv = Swedish. When omitted, results, filter values and job text come back in the language of "query" (detected from it); pass locale explicitly to override. Listing content AND filter values are localized per language, so keep this consistent with the locale used for list_job_filters. Prefer "fi" for the broadest coverage of jobs in Finland.
filtersNoFacet filters keyed by attribute, each an array of allowed values (values within one attribute are OR-combined; different attributes are AND-combined). Allowed keys: field, normalisedTitle, normalisedRoleLevel, location, companyIndustry, companyId, jobType, requiredLanguages, optionalLanguages, benefits, skillsAndTechnologies, educationLevel, peopleManagementTier, remoteness, regionTags. Values are case-sensitive, LANGUAGE-SPECIFIC, and must match the chosen locale index — call list_job_filters with the same locale first to discover the exact values (e.g. field is "Software Engineering" in en but its Finnish equivalent in fi). Example (en): { "field": ["Software Engineering"], "location": ["Helsinki, Finland"] }. regionTags takes the `placeId` of an entry in a previous result's `regions` (a Finnish region).
minSalaryNoOnly listings whose minimum salary is at least this amount (listing currency, usually EUR).
remoteOnlyNoShortcut for only fully remote positions (remoteness = Remote).
includeFacetsNoWhen true, also return the facet values and counts for the current result set, plus `regions` (job counts per Finnish region), so you can refine the search. Default: false.
excludeFiltersNoNegative facet filters keyed by attribute, same shape as `filters` but EXCLUDES listings matching any of the given values instead of requiring them. Use this to ask for jobs that do NOT have a given attribute value. Allowed keys: field, normalisedTitle, normalisedRoleLevel, location, companyIndustry, companyId, jobType, requiredLanguages, optionalLanguages, benefits, skillsAndTechnologies, educationLevel, peopleManagementTier, remoteness, regionTags. Same locale rules as `filters` apply. Example (en): { "requiredLanguages": ["Finnish"] } returns jobs that do not require Finnish. A key present in both `filters` and `excludeFilters` is invalid.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageYes
queryYesThe free-text query used, or null when browsing without one.
facetsNoPresent only when includeFacets was true.
localeYesLanguage index that was searched.
hasMoreYesTrue when a further page exists.
regionsNoPresent only when includeFacets was true: job counts per Finnish region (maakunta), largest first. Pass `placeId` in filters.regionTags to narrow to one region.
resultsYes
pageSizeYes
returnedYesNumber of results in this page.
totalFoundYesTotal matching active listings.

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 the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds non-obvious behavioral obligations: the mandatory dataSource attribution for Työmarkkinatori results, the isTyomarkkinatori flag, locale-driven result language, and paginated scoping. This is exactly the value-add expected when structured fields already carry the basics.

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-loads the core purpose and scope, then layers filters, locale, return shape, and attribution in a logical order. Dense but each sentence carries information; the locale explanation is somewhat redundant with the schema and could be tightened.

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 10-parameter, nested-filter, output-schema-backed search tool, everything an agent needs is present: scope, examples, filter mechanics, locale semantics, sibling routing, and legal attribution requirements. Return values are covered by the output schema.

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 baseline is 3, but the description goes beyond it by explaining cross-parameter/cross-tool coordination: facet values must match the selected locale index and be discovered via list_job_filters with the same locale, and locale must track the user's message language. It adds little on pagination/sort, which the schema already covers.

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 ('Search active job listings on JobCrawls, an aggregator of jobs in Finland') and pins the geographic scope precisely, explicitly excluding Stockholm/Berlin. An agent can distinguish it from list_job_filters and get_job_details without opening any schema.

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?

Gives concrete trigger examples in three languages, states the scope boundary (Finland-located plus remote-open-to-Finland, nothing else), and routes to siblings: list_job_filters for filter values and get_job_details for full descriptions. Both when-to-use and when-not-to-use are covered.

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

All JobCrawls toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources