Skip to main content
Glama

Search LinkedIn jobs

linkedin_search_jobs
Read-onlyIdempotent

Search LinkedIn job listings by keyword, with optional filters for location, hiring company, workplace type, experience level, job type and date posted. Each result includes the job title, company, location, salary when listed and posting date. Read-only: returns public data and changes nothing. Costs 1 credit per result returned, with a minimum of 1 credit per request.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "keyword": "<keyword>",
      "count": "<count>"
    },
    "name": "linkedin_search_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
countYesNumber of results to return (1–100). Defaults to 10.
startNoNumber of results to skip. Defaults to 0.
jobTypeNoRestrict to jobs with this employment type.
keywordYesKeyword(s) to search LinkedIn for, e.g. "openai", "software engineer", "fintech".
locationNoGeographic location to filter jobs by, e.g. "San Francisco Bay Area", "India", "Remote". Defaults to "United States".
cacheOnlyNoReturn only a cached result and never scrape live. With `cacheMaxAgeHours`, only a result that recent is returned; without it, the latest cached result of any age. Responds 404, at no cost, when there is none, e.g. true.
companyIdNoOnly return jobs posted by this company, given as its numeric LinkedIn company ID (the `id` from the company endpoint, or `companyId` on a job result), e.g. "1441".
datePostedNoRestrict to posts published within a recent window.
workplaceTypeNoRestrict to jobs with this workplace arrangement.
experienceLevelNoRestrict to jobs at this seniority level.
cacheMaxAgeHoursNoAccept a cached result scraped up to this many hours ago. A cached result costs no credits, and its `cachedAt` says when it was scraped. When no cached result is that recent, the data is scraped live at the normal price. Leave it out to always scrape live, e.g. 24.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / companyId
      Added value: +{
      +  "description": "Only return jobs posted by this company, given as its numeric LinkedIn company ID (the `id` from the company endpoint, or `companyId` on a job result), e.g. \"1441\".",
      +  "pattern": "^\\d+$",
      +  "type": "string"
      +}
    • changedInput schema / properties / location / description
      Previous value: -"Geographic location to filter jobs by, e.g. \"San Francisco Bay Area\", \"India\", \"Remote\"."New value: +"Geographic location to filter jobs by, e.g. \"San Francisco Bay Area\", \"India\", \"Remote\". Defaults to \"United States\"."
  2. Changed2 schema fields changed
    • addedInput schema / properties / cacheMaxAgeHours
      Added value: +{
      +  "description": "Accept a cached result scraped up to this many hours ago. A cached result costs no credits, and its `cachedAt` says when it was scraped. When no cached result is that recent, the data is scraped live at the normal price. Leave it out to always scrape live, e.g. 24.",
      +  "exclusiveMinimum": 0,
      +  "maximum": 9007199254740991,
      +  "type": "integer"
      +}
    • addedInput schema / properties / cacheOnly
      Added value: +{
      +  "description": "Return only a cached result and never scrape live. With `cacheMaxAgeHours`, only a result that recent is returned; without it, the latest cached result of any age. Responds 404, at no cost, when there is none, e.g. true.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, yet the description still adds real value: a per-result credit cost with a 1-credit minimum, the read-only/public-data nature, and the shape of a result. It does not mention rate limits, throttling, or failure modes, which keeps it short of a 5.

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?

Three compact sentences, front-loaded with purpose and then the filters, result shape, and cost. Slight redundancy in "returns public data and changes nothing," which overlaps the readOnlyHint annotation, but nothing is wasted overall.

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?

With 11 parameters and no output schema, the description compensates by listing the fields in each result (title, company, location, salary, posting date) and disclosing the credit model — both essential for this tool. It is complete enough to call correctly, though the absence of guidance on pagination via `start` and on the cacheOnly cost trade-off leaves a minor gap.

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 100%, so every parameter (including defaults like location="United States" and the cacheOnly/cacheMaxAgeHours interaction) is already documented in the schema. The description only restates the filter categories at a high level and adds no syntax or edge-case semantics beyond that, so the baseline of 3 applies.

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 LinkedIn job listings by keyword") and enumerates the filter dimensions, which cleanly separates it from sibling tools such as linkedin_search_companies, linkedin_search_posts, or linkedin_search_all without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the filter list (the agent can infer this is the tool for keyword+filter job discovery), but there is no explicit when-to-use/when-not guidance and no routing to alternatives such as linkedin_search_all or linkedin_get_company_from_url. The credit-cost note indirectly helps decide between cached and live calls, but the choice itself is left to infer from the schema.

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