Voxjobs (Portugal)

search_jobs

Read-onlyIdempotent

Search active job listings in Portugal. Use this whenever the user wants to find a job — by title, skills, location, salary or schedule. Combines semantic ranking on the query (title/skills) with structural filters. Returns company, city, region, remote mode, seniority, salary and a citable URL, plus total: the exact number of listings matching the filters, which makes this useful for market-size questions. Listings are aggregated from ATSs, boards and public-sector portals and refreshed daily; each result carries postedAt and lastSeenAt. Salaries are published in EUR.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of results (default 10, max 20).
`query`	No	Free-text semantic hint: job title, skills or field (e.g. 'data engineer', 'react developer', 'marketing manager'). Ranks results by meaning; combine with structural filters.
`company`	No	Restrict to jobs from this employer (free-text name).
`escoCode`	No	ESCO occupation code (see europa.eu/esco). Optional and precise: when the caller has one, it filters much more sharply than free text.
`location`	No	City or region within the market (e.g. Lisbon, Porto, Berlin). Do not include the country — it is set by the host.
`schedule`	No	Hours: FULL_TIME, PART_TIME, SHIFTS or FLEXIBLE.
`seniority`	No	Level of the role.
`remoteMode`	No	Work arrangement. REMOTE, HYBRID or ONSITE.
`contractType`	No	Contract type in market-local vocabulary (e.g. permanent, CDI, B2B, umowa o pracę).
`salaryMinYearly`	No	Minimum gross yearly salary, in the market currency (EUR, GBP or PLN). Non-yearly periods are normalised.

Output Schema

TableJSON Schema

Name	Required	Description
`jobs`	Yes
`shown`	Yes
`total`	Yes	Exact number of listings matching the filters.
`market`	Yes
`currency`	Yes

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already mark this read-only, idempotent, and non-destructive; the description adds useful behavioral context: aggregation sources, daily refresh, postedAt/lastSeenAt, semantic ranking, and an exact result total. The only minor caveat is that 'Salaries are published in EUR' sits awkwardly against the schema's EUR/GBP/PLN wording, but it doesn't contradict the annotations.

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?

Six sentences deliver purpose, usage, return value, data provenance, freshness, and currency without repetition. The most important information is front-loaded before the output and behavior details.

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 10-parameter read-only search tool with full schema coverage and an output schema, the description covers searchable criteria, return fields, exact-count behavior, data sources, and refresh cadence. It is slightly less than perfect because it doesn't reconcile the Portugal/EUR framing with the schema's Berlin example and EUR/GBP/PLN currency option.

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 schema already documents all 10 parameters, so the baseline is 3; the description adds value by explaining the semantic-query ranking behavior, how structural filters combine with the query, and how `total` supports market-size questions. It doesn't need to repeat per-parameter details because the schema is complete.

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 opening line states a specific action and resource: searching active job listings in Portugal. It goes on to enumerate search dimensions and distinctive output fields, which clearly separates it from sibling search/similar/detail/stats tools.

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?

It explicitly says to use the tool whenever the user wants to find a job and lists the common criteria, so the intended invocation context is clear. It doesn't name sibling alternatives or give exclusion cases, so it stops at clear context without full when-not guidance.

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

All Voxjobs (Portugal) tools Inspect

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

A4.4/5.0

Disambiguation4/5

Each tool targets a different job-search intent: listing results, a single record, similar roles, salary aggregates, companies, and articles. The only mild overlap is search_jobs vs get_salary_stats, since both accept the same filters and can report match counts, but their outputs and suggested use cases are clearly differentiated.

Naming Consistency5/5

All six tools use lowercase snake_case with a leading verb (search_, get_, find_) followed by the resource. The pattern is uniform and predictable across search_articles, search_companies, search_jobs, get_job_detail, get_salary_stats, and find_similar_jobs.

Tool Count5/5

Six tools is well-scoped for a Portugal job-market server: search, detail, similar-jobs, salary stats, companies, and articles each cover a distinct use case. There are no redundant or filler tools.

Completeness4/5

The read-only job search workflow is well covered: discover jobs, open details, find alternatives, compare salaries, explore employers, and read guidance. Minor gaps remain, such as no dedicated article-detail drill-down or company-profile tool, but agents can likely complete core tasks.

Resources

Need Help?