Social Fetch

Search LinkedIn jobs

linkedin_live_jobs_search_v2

Read-only

Search LinkedIn jobs by keyword and filters. Returns a list (use cursor when paginated).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`sort`	No	Alias for `sortBy`. Prefer `sortBy`.
`trim`	No	Ignored if this tool does not support it.
`count`	No
`limit`	No	Alias for `count`. Prefer `count`.
`start`	No
`cursor`	No
`offset`	No	Ignored if this tool does not support it.
`salary`	No
`sortBy`	No		relevance
`titles`	No
`context`	Yes	Describe the user's underlying goal in one sentence — not the tool you are calling.
`keyword`	No
`benefits`	No
`jobTypes`	No
`pageSize`	No	Alias for `count`. Prefer `count`.
`companies`	No
`easyApply`	No	Accepts a native boolean, or the string `true`/`false`/`1`/`0` (case-insensitive).
`functions`	No
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`locations`	No
`datePosted`	No
`experience`	No
`fairChance`	No	Accepts a native boolean, or the string `true`/`false`/`1`/`0` (case-insensitive).
`industries`	No
`maxResults`	No	Alias for `count`. Prefer `count`.
`commitments`	No
`max_results`	No	Alias for `count`. Prefer `count`.
`verifiedJob`	No	Accepts a native boolean, or the string `true`/`false`/`1`/`0` (case-insensitive).
`workplaceTypes`	No
`conversation_id`	No	Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.
`under10Applicants`	No	Accepts a native boolean, or the string `true`/`false`/`1`/`0` (case-insensitive).

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedSep 21, 2026

addedInput schema / properties / limit

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `count`. Prefer `count`."
+}

addedInput schema / properties / maxResults

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `count`. Prefer `count`."
+}

addedInput schema / properties / max_results

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `count`. Prefer `count`."
+}

addedInput schema / properties / offset

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

addedInput schema / properties / pageSize

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `count`. Prefer `count`."
+}

addedInput schema / properties / sort

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Alias for `sortBy`. Prefer `sortBy`."
+}

addedInput schema / properties / trim

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "number"
+    },
+    {
+      "type": "boolean"
+    }
+  ],
+  "description": "Ignored if this tool does not support it."
+}

AddedSep 19, 2026

TDQS

B3.3/5.0

Behavior4/5

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

Annotations already cover readOnlyHint and openWorldHint, so the description's burden is lower. It adds useful behavioral context beyond those annotations: the tool returns a list and pagination is cursor-based. No contradiction with annotations.

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 appropriately concise — one sentence with the action front-loaded and the pagination note adding value. It is not bloated, though it could include a bit more guidance (e.g., which filters are supported) without losing tightness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a 31-parameter tool with no output schema, and the description is minimal. It mentions the return type (a list) and cursor pagination, but does not explain available filters, the required context and llm_model parameters, or any detail about the response structure. An agent would need substantial schema digging to invoke it correctly.

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

Parameters2/5

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

Schema description coverage is only 45%, well below 50%, so the description needs to compensate by explaining key parameters or filter semantics. It only says 'by keyword and filters' without detailing any of the 31 parameters, failing to help the agent understand what filters exist or how to use them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Search') and resource ('LinkedIn jobs'), and specifies the mechanism ('by keyword and filters'). It is clear and directly aligned with the tool's name and title, though it does not explicitly differentiate from sibling job tools like linkedin_live_job_get_v2 or linkedin_live_job_similar_v2, so it stops short of a 5.

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?

The description implies the primary use case (searching jobs with keyword and filters) and gives one piece of concrete usage guidance: 'use cursor when paginated.' However, it does not mention alternatives or exclusions, such as when to use a job-get or organization-jobs tool instead, so the guidance is implied rather than explicit.

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

All Social Fetch 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.

Search LinkedIn jobs

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources