Skip to main content
Glama

Metaintro Job Search

Search jobs

search_jobs
Read-onlyIdempotent

Search live job postings from employer career sites and job boards by role or keywords, place, remote work, employment type and pay. Returns up to 10 job cards a page; each card has fit (every applied filter as met, partial, unknown or not_met, and a verdict of match or near_match), posting (age, freshness, last seen live), an indexed pay amount when there is one (posted by the employer only when salary.salarySource is structured, provider, page_text or extracted; otherwise unconfirmed), and the employer's title and summary as source text. coverage says what was searched and whether more pages exist; for the next page, call search_jobs again with continuationInput unchanged, which keeps the filters this search resolved, and page with offset only when it is absent. filters.jobTypes takes FULL_TIME, PART_TIME, CONTRACT or other listed types, any of which match; filters.salaryListedOnly keeps only jobs that list pay; filters.minSalary is annual pay in the requested currency, and ranges that overlap it are included. Licence requirements and eligibility are not assessed. Use it to find openings from a description; use get_job to read one posting in full, find_similar_jobs for more like a known job, list_company_jobs for one employer, and get_market_insights or get_local_demand for counts instead of jobs.

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": {
      "query": "<query>"
    },
    "name": "search_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
cursorNo
localeNo
offsetNo
filtersNo
purposeNo
variantsNoUp to 4 more wordings of the same search, such as other job titles for the same work. They run at the same time as query, with the same filters, radius, limit and page, and each counts as one search toward the search limit. Results come back in variants, one entry per wording, leaving out jobs already listed above them; repeatedJobIds names those. Use this instead of separate searches for alternative titles.
commuteRadiusMilesNo
fallbackToVisitorPlaceNoWhen the query names no place and the search is not remote, search the signed-in person's saved country, or the country of an anonymous visitor's IP address.

Output Schema

NameRequiredDescriptionDefault
jobsNo
errorNo
coverageNo
fallbackNo
searchIdNo
variantsNo
nextStepsYes
totalCountNo
remainingJobsNo
assistantGuidanceYes
continuationInputNo
totalCountIsExactNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "assistantGuidance": {
      +      "type": "string"
      +    },
      +    "continuationInput": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "coverage": {
      +      "properties": {
      +        "exactTitle": {
      +          "type": "string"
      +        },
      +        "fullMatches": {
      +          "type": "number"
      +        },
      +        "morePages": {
      +          "type": "boolean"
      +        },
      +        "nearMatches": {
      +          "type": "number"
      +        },
      +        "nextOffset": {
      +          "type": [
      +            "number",
      +            "null"
      +          ]
      +        },
      +        "noResults": {
      +          "type": "string"
      +        },
      +        "pageCutToFit": {
      +          "type": "boolean"
      +        },
      +        "places": {
      +          "type": "string"
      +        },
      +        "returned": {
      +          "type": "number"
      +        },
      +        "scope": {
      +          "type": "string"
      +        },
      +        "searchedFor": {
      +          "type": "string"
      +        },
      +        "totalCount": {
      +          "type": "number"
      +        },
      +        "totalCountIsExact": {
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "error": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "fallback": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "jobs": {
      +      "items": {
      +        "properties": {
      +          "applicationRules": {
      +            "type": "array"
      +          },
      +          "applyUrl": {
      +            "type": "string"
      +          },
      +          "category": {
      +            "type": "string"
      +          },
      +          "companyLogoMarkSrc": {
      +            "type": "string"
      +          },
      +          "companyName": {
      +            "type": "string"
      +          },
      +          "companySlug": {
      +            "type": "string"
      +          },
      +          "distanceMi": {
      +            "type": "number"
      +          },
      +          "employerUrl": {
      +            "type": "string"
      +          },
      +          "fit": {
      +            "type": [
      +              "object",
      +              "null"
      +            ]
      +          },
      +          "hybridOk": {
      +            "type": "boolean"
      +          },
      +          "id": {
      +            "type": "string"
      +          },
      +          "industryScope": {
      +            "type": "string"
      +          },
      +          "jobTypes": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "locationProximity": {
      +            "type": "string"
      +          },
      +          "locations": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "metaintroUrl": {
      +            "type": "string"
      +          },
      +          "postedOn": {
      +            "type": "string"
      +          },
      +          "posting": {
      +            "type": [
      +              "object",
      +              "null"
      +            ]
      +          },
      +          "relatedRole": {
      +            "type": "boolean"
      +          },
      +          "remoteOk": {
      +            "type": "boolean"
      +          },
      +          "salary": {
      +            "type": [
      +              "object",
      +              "null"
      +            ]
      +          },
      +          "salaryIssue": {
      +            "type": "string"
      +          },
      +          "seniorityLevel": {
      +            "type": "string"
      +          },
      +          "summary": {
      +            "type": "string"
      +          },
      +          "title": {
      +            "type": "string"
      +          },
      +          "url": {
      +            "type": "string"
      +          },
      +          "workplaceType": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "id"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "nextSteps": {
      +      "items": {
      +        "properties": {
      +          "action": {
      +            "type": "string"
      +          },
      +          "ask": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "input": {
      +            "type": "object"
      +          },
      +          "tool": {
      +            "type": "string"
      +          },
      +          "url": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "action"
      +        ],
      +        "type": "object"
      +      },
      +      "maxItems": 3,
      +      "type": "array"
      +    },
      +    "remainingJobs": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "searchId": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "totalCount": {
      +      "type": [
      +        "number",
      +        "null"
      +      ]
      +    },
      +    "totalCountIsExact": {
      +      "type": [
      +        "boolean",
      +        "null"
      +      ]
      +    },
      +    "variants": {
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "assistantGuidance",
      +    "nextSteps"
      +  ],
      +  "type": "object"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / filters / properties / companySlug
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 200,
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, open-world and non-destructive behavior, and the description adds real substance on top: up to 10 cards per page, the fit/posting/pay/coverage card shape, what coverage reports, and that licence/eligibility are out of scope. The one weakness is that pagination is described in terms of "continuationInput unchanged" and "page with offset only when it is absent", but the schema exposes cursor and offset and no continuationInput, which risks confusing an agent about how to page.

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 dense but front-loaded: purpose first, then return shape, then pagination, then filter semantics, then sibling routing. Every clause carries information, though the pagination sentence is convoluted ("which keeps the filters this search resolved") and could be stated more plainly.

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 10-parameter, nested-schema search tool this covers the essentials: filtering scope, page size, how to continue, how to interpret fit and pay provenance, and which sibling to use instead. Return values are also partly explained despite an output schema existing, and the stated limitations (licence/eligibility not assessed) close the main expectation 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 only 20%, so the description must carry weight, and it does explain a handful: jobTypes accepted values and any-of matching, salaryListedOnly, minSalary as annual pay in the requested currency with overlapping ranges included. Many other parameters — cursor, offset, limit, locale, variants, commuteRadiusMiles, fallbackToVisitorPlace, postedOn, industry, companySlug, titleContains/Excludes — are left to the schema with no added meaning.

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 live job postings from employer career sites and job boards") plus the facets it can search on — role/keywords, place, remote work, employment type, pay. That is enough for an agent to distinguish it from get_job, find_similar_jobs, list_company_jobs and get_market_insights without opening any 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?

Explicitly routes the agent: "Use it to find openings from a description" and names each sibling with the condition that selects it (read one posting, more like a known job, one employer, counts instead of jobs). It also states a negative boundary — licence requirements and eligibility are not assessed — so the agent knows what this search cannot answer.

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