Skip to main content
Glama

Jobily Jobs

by gr.jobily

Search jobs

search_jobs
Read-onlyIdempotent

Search job listings on Jobily.gr, the Greek job board. Filter by free-text term, role/location/sector slugs, company, employment type, workplace type and work time. Use lookup_roles_and_companies, lookup_locations and list_sectors to discover valid slugs — unrecognized slug filters are reported in matchedCriteria.unrecognizedTerms and ignored by the search. Returns up to 20 jobs per page with the total count, facet counts (first page) and recovery suggestions when nothing matches. Search results do not include job descriptions — call get_job with a result's guid for the full posting. When total is large (100+) and few filters are active, recommend the user narrow their search using the facets or lookup tools rather than paginating through hundreds of results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number, 1-indexed (default 1). Each page returns up to 20 jobs.
roleNoRole slug, e.g. 'software-engineer'. Discover via lookup_roles_and_companies.
sectorNoSector slug, e.g. 'information-technology-it'. Discover via list_sectors.
companyNoCompany slug (from lookup_roles_and_companies) or company GUID.
locationNoLocation slug, e.g. 'athens', 'thessaloniki'. Discover via lookup_locations. Omit for all of Greece.
searchTermNoFree-text search term, Greek or English (e.g. 'πωλητής', 'software engineer'). Prefer the role filter when a role slug is known.
workTimeTypeNoOne of: full-time, part-time.
workplaceTypeNoOne of: remote, hybrid, onsite.
employmentTypeNoOne of: permanent, contract, internship, seasonal, volunteer.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds substantial behavioral detail beyond them: unrecognized slug filters are ignored and reported, pages are limited to 20 jobs, facet counts appear on the first page, recovery suggestions are available, and job descriptions are omitted from results. No contradiction with annotations exists.

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

Conciseness5/5

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

While the description is long, every sentence earns its place: purpose, filter dimensions, slug discovery, pagination/facets, absence of descriptions, and large-result guidance. It is front-loaded with the core action and resource, and the density is justified by the tool's complexity.

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?

With no output schema, the description adequately explains return characteristics: page size, total count, first-page facet counts, recovery suggestions, and the need to call get_job for full descriptions. It also covers multi-tool coordination and search-narrowing guidance, making the tool fully usable without external docs.

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?

The input schema already fully documents all 9 parameters with 100% coverage, so the baseline is 3. The description adds extra semantic value by explaining that unrecognized slugs are ignored and reported in matchedCriteria.unrecognizedTerms, and by recommending the role filter over free-text search when a role slug is known.

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?

The description opens with a specific verb and resource: 'Search job listings on Jobily.gr'. It enumerates the filtering dimensions and distinguishes itself from siblings by noting that get_job retrieves full postings and lookup tools discover valid slugs.

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?

The description explicitly directs agents to lookup_roles_and_companies, lookup_locations, and list_sectors for discovering valid slugs. It additionally states when to call get_job instead, and when pagination is inappropriate due to large result sets.

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

All Jobily Jobs toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

Each tool targets a distinct resource and action: get_job retrieves details, search_jobs performs queries, list_sectors and lookup_locations provide filter facets, and lookup_roles_and_companies handles role/company suggestions. There is no overlap in purpose, and the descriptions clearly differentiate the roles.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (get_, list_, lookup_, search_). Although the verbs vary, the pattern is uniform and predictable, matching the style of well-organized RESTful or MCP naming conventions.

Tool Count5/5

Five tools form a compact, well-scoped set for a job-search read API. This falls comfortably within the ideal 3-15 range, and each tool serves a necessary purpose without redundancy.

Completeness5/5

The tool surface fully covers the core job-listing workflow: facet discovery (sectors, locations, roles/companies), searching/filtering, and retrieving full details. No missing operations are apparent for a read-only job board; common gaps like update/delete are out of scope for this server.

Resources