Skip to main content
Glama

LexGO Jobs

Search LexGO jobs

search_jobs
Read-onlyIdempotent

Search live Belgian or Luxembourg legal jobs on LexGO by keywords and filters. q works best with one to three keywords, such as advocaat, juriste Bruxelles or M&A. Every word has to match a job's title, employer, practice area, function, city or region, in Dutch, French or English, and generic words such as jobs, vacature or legal are ignored. Returns 10 compact results without descriptions unless limit says otherwise. get_job returns a vacancy's full description. click_url is the link to the vacancy on LexGO.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoOne to three keywords, such as advocaat, juriste Bruxelles or M&A. Every word has to match a job's title, employer name, practice area, function, city or region, in Dutch, French or English. Simple plurals match, and generic words such as jobs, vacature, legal or Belgium are ignored; with nothing left, q is ignored. A word in no job gives no results. LIKE wildcards are treated as characters.
limitNo
cursorNo
domainNo
remoteNo
contractNo
languageNoPosting content locale (nl/fr/en), not required spoken languages.
region_idNoRegion id: 1 Brussels, 2 Antwerp, 3 Flemish Brabant, 4 East Flanders, 5 West Flanders, 6 Limburg, 7 Walloon Brabant, 8 Namur, 9 Hainaut, 10 Liège, 11 Luxembourg, 12 Luxembourg (country), 13 Netherlands, 14 France, 15 Other country. 11 is the Belgian province, 12 the country. A province also matches jobs posted for a whole area (Flanders, Wallonia, Belgium), which list every province they cover in regions.
function_idNo
discipline_idNoPractice-area id from GET /api/v1/taxonomies.
experience_idNoExperience band id from GET /api/v1/taxonomies (0 unknown, 1 0-3 years, 2 3-6, 3 +6).
work_environment_idNoEmployer-type id from GET /api/v1/taxonomies.

Output Schema

NameRequiredDescriptionDefault
jobsNo
next_cursorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / limit / default
      Added value: +10
    • changedInput schema / properties / q / description
      Previous value: -"Literal match on titles, employer name, and practice-area names. LIKE wildcards are treated as characters."New value: +"One to three keywords, such as advocaat, juriste Bruxelles or M&A. Every word has to match a job's title, employer name, practice area, function, city or region, in Dutch, French or English. Simple plurals match, and generic words such as jobs, vacature, legal or Belgium are ignored; with nothing left, q is ignored. A word in no job gives no results. LIKE wildcards are treated as characters."
    • changedInput schema / properties / region_id / description
      Previous value: -"Address region id (Address::REGIONS). Never jobs.region_id. Also matches jobs posted for a whole area (Flanders, Wallonia, Belgium), which list every province they cover in regions."New value: +"Region id: 1 Brussels, 2 Antwerp, 3 Flemish Brabant, 4 East Flanders, 5 West Flanders, 6 Limburg, 7 Walloon Brabant, 8 Namur, 9 Hainaut, 10 Liège, 11 Luxembourg, 12 Luxembourg (country), 13 Netherlands, 14 France, 15 Other country. 11 is the Belgian province, 12 the country. A province also matches jobs posted for a whole area (Flanders, Wallonia, Belgium), which list every province they cover in regions."
  2. Changed1 schema field changed
    • changedInput schema / properties / region_id / description
      Previous value: -"Address region id (Address::REGIONS). Never jobs.region_id."New value: +"Address region id (Address::REGIONS). Never jobs.region_id. Also matches jobs posted for a whole area (Flanders, Wallonia, Belgium), which list every province they cover in regions."
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the read-only, idempotent, non-destructive annotations, the description discloses important search behavior: every keyword must match certain fields, generic words are ignored, and results are compact with 10 returned by default unless limit overrides it. It also explains that click_url links to LexGO, though it does not describe cursor-based pagination or all filter behaviors.

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?

The description is front-loaded with purpose and query behavior, and most sentences carry useful operational detail. Some wording repeats schema-level q guidance, and the click_url explanation is less necessary because an output schema exists, but overall it remains efficient.

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?

Given the presence of annotations and an output schema, the description is largely complete for a search tool: it explains the query model, result compactness, default limit behavior, and the get_job handoff. The main remaining gap is pagination via cursor and consistent explanation of the many optional filters.

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 50%, so the schema already documents several important parameters including q, language, region_id, discipline_id, experience_id, and work_environment_id. The description adds meaning mainly for q matching and the default result count controlled by limit, but it does not compensate for undocumented parameters such as cursor, domain, remote, contract, or function_id.

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 states a specific verb and resource: searching live Belgian or Luxembourg legal jobs on LexGO. It distinguishes the tool from get_job by explaining that get_job returns a vacancy's full description, while this search returns compact results.

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 clearly frames the tool as keyword-and-filter search and gives practical query guidance, including the one-to-three-keyword recommendation and the fields matched. It also points to get_job for full vacancy descriptions, but it does not explicitly cover when to use filters instead of q or when not to use this tool.

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.

Resources