Manifold MCP

Search job postings

leads_search_jobs

Read-onlyIdempotent

Open job postings Google Jobs lists for a role: employer, location, salary and where it is posted, from LinkedIn, Indeed, other boards and company careers sites.

Use when: "which companies are hiring an SEO manager in London", hiring for a role as a buying signal, "who is hiring people who use HubSpot", what a role pays. Not for: every opening at one company, which Google Jobs does not answer (a company's name in the keyword finds jobs that mention it); read its careers page with seo_get_page. People who already hold a role, use leads_search_people. Returns: Record. keyword, rows[]: rank, job_id, title, company, company_url, location, source (the board or careers site), url (the posting there), salary (as written), contract_type, posted (YYYY-MM-DD, only to the day). No description text. One role on several boards can fill several rows. Cost: 1 credit per 20 results. Default 20 = 1 credit. Cached 1 day. Can take up to a minute. Example: {"keyword": "seo manager", "location": "London,England,United Kingdom"}

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>"
    },
    "name": "leads_search_jobs"
  }
}

Input Schema

Name	Required	Description	Default
`depth`	No	Most rows to return. Default 20, max 200, billed per 20.
`dry_run`	No	Return only meta with the estimate. Costs nothing.
`keyword`	Yes	A role or skill, as a job seeker would search it: "seo manager", "hubspot".
`language`	No	ISO 639-1 language code. Default en.	en
`location`	No	Provider location name or code. Default United States.	United States
`max_credits`	No	Refuse with BudgetExceeded if the estimate is higher.
`employment_type`	No	Only these types; every type when empty. partime is Google's spelling.

Output Schema

Name	Required	Description	Default
`meta`	Yes
`rows`	No
`error`	No
`hints`	Yes
`keyword`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 11, 2026

changedOutput schema / properties / meta / properties / monitor_offer / description

Previous value: -"This lookup came back on another day: after the task, offer the user once a monitor that repeats it, previewing its cost first."New value: +"This lookup came back on another day: after the task, offer the user once a monitor that repeats it, previewing it first."

removedOutput schema / properties / meta / properties / monitor_offer / properties / est_credits_month
```
Removed value: -{
-  "type": "number"
-}
```

changedOutput schema / properties / meta / properties / monitor_offer / required

Previous value: -[
-  "preset",
-  "fields",
-  "cadence",
-  "est_credits_month",
-  "message"
-]New value: +[
+  "preset",
+  "fields",
+  "cadence",
+  "message"
+]

Changed1 schema field changedNov 8, 2026

addedOutput schema / properties / meta / properties / monitor_offer

Added value: +{
+  "additionalProperties": false,
+  "description": "This lookup came back on another day: after the task, offer the user once a monitor that repeats it, previewing its cost first.",
+  "properties": {
+    "cadence": {
+      "type": "string"
+    },
+    "est_credits_month": {
+      "type": "number"
+    },
+    "fields": {
+      "additionalProperties": {},
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "message": {
+      "type": "string"
+    },
+    "preset": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "preset",
+    "fields",
+    "cadence",
+    "est_credits_month",
+    "message"
+  ],
+  "type": "object"
+}

AddedNov 8, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description goes well beyond them: 1 credit per 20 results, 1-day cache, up to a minute latency, and the caveat that one role on several boards produces duplicate-looking rows. It also states the response carries no description text, which prevents a downstream agent from expecting job bodies.

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?

Front-loads purpose, then scopes usage, then returns, cost and an example in labeled blocks that are easy to scan. The Returns list is partly redundant with the existing output schema, which is the main wasted text; everything else is dense and load-bearing.

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 7-parameter, cost-bearing, open-world search tool, the definition covers routing, billing, latency, dedupe behavior and field shape. With an output schema present it needn't explain return values further, and nothing an agent needs to call this safely is missing.

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?

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by clarifying keyword semantics — that a company name in the keyword finds jobs merely mentioning it, not that company's postings — and by including a worked location example ("London,England,United Kingdom"). Depth, dry_run and max_credits are left entirely to the schema.

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?

Opens with a specific verb+resource ("Open job postings Google Jobs lists for a role") and enumerates the returned facets: employer, location, salary and posting source. It explicitly separates itself from leads_search_people and seo_get_page, so an agent can route correctly without opening a schema.

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

Usage Guidelines5/5

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

Provides concrete trigger phrases ("which companies are hiring an SEO manager in London", "who is hiring people who use HubSpot", what a role pays) plus a "Not for" clause naming the sibling to use instead for each excluded case. The exclusion of "every opening at one company" even explains why Google Jobs can't answer it.

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

All Manifold MCP 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.

Resources

Need Help?