ZOOQ - LinkedIn Data for AI Agents

search_jobs

Read-onlyIdempotent

Job/opportunity search with the full filter set. Location filtering works: pass locations a LinkedIn geo id (e.g. 101570771 for Tel Aviv-Yafo) — see that parameter for how to find one, and note it is an EXACT match, so use a city id rather than a country id. Still id-typed and not yet usable: titles, industries, functions, benefits, commitments. Offset-paginated. data.jobs[].id is the opportunityEntityId consumed by /jobs/details-v2, /jobs/similar, /jobs/people-also-viewed, /jobs/hiring-team. (Costs 10 Zooq credits.)

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

Name	Required	Description
`count`	No	Results per page, 0-50 (default 25).
`start`	No	Pagination offset, 0-999.
`salary`	No	Minimum salary bucket. Accepted values: 20k, 30k, 40k, 50k, 60k, 70k, 80k, 90k, 100k.
`sortBy`	No	Result ordering. Accepted values: relevance, date_posted.
`titles`	No	Title id(s), comma-separated. NOT free text: a title like 'Senior Full Stack Developer' is rejected upstream (surfaces as a 422 mentioning entityId; no credits charged). Use `keyword` for free-text role matching instead.
`keyword`	No	Free-text keyword.
`benefits`	No	Benefits filter, comma-separated.
`jobTypes`	No	Job type. Accepted values: full_time, part_time, contract, temporary, internship, volunteer, other. Comma-separate for multiple.
`companies`	No	Numeric organization id(s), comma-separated (e.g. 1035). Get from job payloads — data.jobs[].organization.organizationId via companies_jobs.
`easyApply`	No	Only Easy Apply jobs. Accepted values: true, false.
`functions`	No	Job-function id(s), comma-separated. Free text is not reliably accepted — see the note on `locations`.
`locations`	No	Geo entity id(s), comma-separated. This is LinkedIn's own public geo id. To find the id for a location: • Type your target city, state or country into the location search box on LinkedIn • Select the correct match from the auto-complete dropdown list • Press enter to load the search results page • Check the browser address bar for geoId= followed by a long number sequence NOTE: this ID is case sensitive. Jobs may appear on LinkedIn but not here, because LinkedIn shows results for proximate locations while this search is exact-match based. Prefer a CITY id over a country id for the same reason — postings are tagged with the exact city, so Tel Aviv-Yafo (101570771) returns results where Israel (101620260) returns none.
`datePosted`	No	Recency filter. Accepted values: 24h, 1week, 1month.
`experience`	No	Experience level. Accepted values: internship, entry_level, associate, mid_senior, director, executive. Comma-separate for multiple.
`fairChance`	No	Only fair-chance employer jobs. Accepted values: true, false.
`industries`	No	Industry id(s), comma-separated. Free text is not reliably accepted — see the note on `locations`.
`commitments`	No	Company-commitment filter, comma-separated.
`verifiedJob`	No	Only verified job postings. Accepted values: true, false.
`workplaceTypes`	No	Workplace type. Accepted values: onsite, remote, hybrid. Comma-separate for multiple.
`under10Applicants`	No	Only jobs with under 10 applicants. Accepted values: true, false.

Output Schema

Name	Required	Description	Default
`jobs`	No	Array in the example
`total`	No	Example value was a number

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 1, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses exact-match location behavior, the fact that results may differ from LinkedIn's own UI, offset pagination, a 10-credit cost, and that some accepted id filters are not yet usable. This is rich, non-obvious behavioral context.

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?

The description is dense but compact. Six sentences cover purpose, location handling, unusable filters, pagination, downstream id usage, and cost, with the core purpose stated first and no filler.

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 20-parameter search tool with an output schema, the description covers the remaining decision-critical context: pagination, exact-match limitations, unusable parameters, downstream consumers of the returned jobs, and credit cost. Nothing essential is missing for correct selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the prose adds important cross-parameter meaning: it flags id-typed filters that are not yet usable, explains how to find LinkedIn geo ids, and warns that titles must be ids rather than free text. These caveats are not fully present in every individual parameter description.

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 phrase "Job/opportunity search with the full filter set" clearly identifies both the operation and the resource. The description also connects the returned data.jobs[].id to downstream job endpoints, distinguishing it from detail tools and other search tools in the sibling list.

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?

The description gives actionable usage guidance: which filters work, which are not yet usable, and how the returned ids feed /jobs/details-v2 and related endpoints. It does not explicitly name alternative search tools for when not to use this one, but the downstream-consumer note strongly implies its role.

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

All ZOOQ - LinkedIn Data for AI Agents tools Inspect

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.