Skip to main content
Glama

Search published openings

search_jobs
Read-onlyIdempotent

Search current openings that companies publish on rolefig, across every company. Filter by keywords (q), workplace, employment type, country (ISO code), region (a code such as CA), company slug, postedWithin (7 or 30 days) and minPay (minimum annual USD); sort by newest, pay or distance. Add near (a California ZIP, city, county or region such as Inland Empire) with radius (5, 10, 25, 50 or 100 miles), pay (minimum $/hour), shift (day, evening, night, repeatable), noWeekends, noLicense, spanish and payShown (only openings that show pay). Openings that don't state a chosen fact come after the ones that fit, with fit unstated. For the next page, repeat the search with nextCursor as after. Each opening has the company's application URL and its rolefig page; rolefig never submits applications.

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
qNo
payNo
nearNo
sortNo
typeNo
afterNo
areasNo
limitNo
shiftNo
minPayNo
radiusNo
regionNo
companyNo
countryNo
spanishNo
payShownNo
noLicenseNo
workplaceNo
noWeekendsNo
postedWithinNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / areas
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "1",
      +        "true"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "const": true,
      +      "type": "boolean"
      +    }
      +  ]
      +}
    • addedInput schema / properties / near
      Added value: +{
      +  "maxLength": 100,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / noLicense
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "1",
      +        "true"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "const": true,
      +      "type": "boolean"
      +    }
      +  ]
      +}
    • addedInput schema / properties / noWeekends
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "1",
      +        "true"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "const": true,
      +      "type": "boolean"
      +    }
      +  ]
      +}
    • addedInput schema / properties / pay
      Added value: +{
      +  "exclusiveMinimum": 0,
      +  "maximum": 500,
      +  "type": "number"
      +}
    • addedInput schema / properties / payShown
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "1",
      +        "true"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "const": true,
      +      "type": "boolean"
      +    }
      +  ]
      +}
    • addedInput schema / properties / radius
      Added value: +{
      +  "type": "number"
      +}
    • addedInput schema / properties / shift
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "day",
      +        "evening",
      +        "night"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "items": {
      +        "enum": [
      +          "day",
      +          "evening",
      +          "night"
      +        ],
      +        "type": "string"
      +      },
      +      "maxItems": 3,
      +      "type": "array"
      +    }
      +  ]
      +}
    • removedInput schema / properties / sort / default
      Removed value: -"newest"
    • changedInput schema / properties / sort / enum
      Previous value: -[
      -  "newest",
      -  "pay"
      -]New value: +[
      +  "newest",
      +  "pay",
      +  "distance"
      +]
    • addedInput schema / properties / spanish
      Added value: +{
      +  "anyOf": [
      +    {
      +      "enum": [
      +        "1",
      +        "true"
      +      ],
      +      "type": "string"
      +    },
      +    {
      +      "const": true,
      +      "type": "boolean"
      +    }
      +  ]
      +}
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive, and the description adds real behavior beyond them: the ordering rule for openings missing a chosen fact, pagination via nextCursor, the returned fields (company application URL and rolefig page), and the explicit caveat that rolefig never submits applications. It does not mention result sizes or limits, but the behavioral picture is substantially richer than the annotations alone.

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?

Purpose is front-loaded and the dense sentences all carry information; almost nothing is padding. The long parameter enumeration reads as a run-on rather than a scannable list, and "shift (day, evening, night, repeatable)" introduces a value not present in the shift enum, which costs a point on clarity.

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?

For a 20-parameter tool with no schema descriptions and no output schema, the definition covers nearly everything needed: filter meanings, sort options, pagination, ordering behavior, and what each result contains. Remaining gaps are minor — limit (default 50, max 100) and the areas flag are never explained.

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?

With 0% schema description coverage across 20 parameters, the description carries the full burden and largely delivers: it names q, workplace, employment type, country as ISO code, region as a code (e.g., CA), company slug, postedWithin (7 or 30 days), minPay in annual USD, sort values, and the near/radius pairing with concrete radius options. It also disambiguates pay (hourly minimum) from minPay (annual USD) and documents the boolean-ish flags noWeekends, noLicense, spanish, payShown — meaning the schema alone would not convey.

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?

States a specific verb and resource ("Search current openings") plus the scope ("across every company"), which contrasts with the company-scoped sibling list_company_openings. An agent can tell what this returns and how it differs from per-company listing without opening the schema.

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?

Filter and sort semantics are covered thoroughly and pagination is explained ("repeat the search with nextCursor as after"), which implies when to use it. However, it never names an alternative (e.g., get_job for a single opening, list_company_openings for one employer) or states when not to use this tool, leaving selection guidance to inference.

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