Skip to main content
Glama
foundrole

FoundRole Jobs - AI Job Search & Application Tracker

Official

Search jobs

jobs_search

Search real-time job listings by title, location, company, and filters to find matching roles and return job details.

Instructions

Searches a database for real-time job listings matching the user's criteria.

The query is the full job title or role: "Ruby Developer" or "Ruby on Rails Engineer" rather than a bare keyword like "Ruby", which is too broad and matches unrelated fields. Results may be filtered by location, company, and how recently a job was posted.

Each result carries an id and resultItemId; jobs_details takes that id with the corresponding result_item_id and returns the job's full description, requirements, and benefits. The response also carries a nextCursor for the next page of results; a follow-up page is fetched by passing only that cursor, with no other search parameters.

With a ready profile, a query for the profile's target profession or an omitted query uses the same personalized feed as jobs_recommendations and the website. A different or unrecognized profession uses general job search, preserving the explicit query and filters. An omitted location uses the profile location. Without a ready profile, search uses the general job listings. Job details include FoundRole salary benchmarks, H-1B sponsorship signals, E-Verify status, and job-trust analysis; list-level employer signals follow the user's current entitlements.

Constraints in the user's request — remote-only work, H1B sponsorship, a minimum salary, hiding risky postings, a minimum match grade — are the search parameters remote, h1b_sponsors_only, salary_floor, hide_low_quality, and min_match; sort orders the results by relevance, newest, salary or personal match. The search enforces only constraints passed as parameters; a constraint left out of the call is not applied to the result set.

Job type, work mode, required education, experience level, benefits, bonuses, employers to include or exclude, and the search radius are the parameters employment_types, work_modes, education, experience_levels, benefits, bonuses_only, companies, exclude_companies and radius. Remote and hybrid are independent work modes: a remote search never returns hybrid jobs. A job that does not state the filtered attribute is left out while that filter is set. Fully remote work that can be done from the requested location is strict_remote, with confirmed_work_from to require a stated work-from area; one brand inside a company is hiring_brand next to company.

Advanced filters (sort, min_match, h1b_sponsors_only, hide_low_quality, salary_floor, remote, strict_remote, confirmed_work_from, work_modes, benefits, bonuses_only, companies, exclude_companies; sort only when ordering by salary or match, companies only when it names more than one employer) apply for every account. Without FoundRole Pro, a search using one returns the first few matching jobs and the number of further matches; FoundRole Pro accounts receive the whole list. The other parameters never shorten the results.

Each response includes a system_instruction describing how to present the results for the current client.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoResult order (score, posted_at, match, salary): score is relevance and the default, posted_at is newest first, salary is highest pay first, match is best personal fit first and needs a resume. Ordering by salary or match is an advanced option.
queryNoThe full job title or skill (e.g., "Ruby Developer", NOT just "Ruby")
cursorNoPagination cursor. Treat as an opaque string. COPY EXACTLY.
radiusNoSearch radius in miles around a city location (default 40); not used for state, country or remote searches.
remoteNoAdvanced filter: only remote-eligible jobs, matched across the whole country of the requested location rather than its radius.
companyNoThe official company name
benefitsNoAdvanced filter: benefit names such as "health insurance", "401k" or "parental leave"; a job qualifies only when it states every listed benefit. Names that match no known benefit are ignored.
locationNoGeographic location (e.g., 'Boston, MA')
companiesNoFilter: official company names; a job from any of them qualifies, across every job board each employer posts on. More than one company makes it an advanced filter. Next to company, a job has to match both; hiring_brand narrows company only.
educationNoFilter: jobs whose posting requires one of these education levels (no_requirements, high_school, associate_degree, bachelor_degree, professional_certificate, postgraduate_degree); bachelor_degree means the posting asks for a bachelor degree, not that it suits someone holding one.
min_matchNoAdvanced filter: lowest personal FoundRole match grade to keep, the same letter each job shows in insights.match.grade. A and A- are rare even for a strong resume; B keeps good and strong matches; C+ also keeps fair ones. Needs a resume on the account.
work_modesNoAdvanced filter: jobs in any of these work modes (on_site, remote, hybrid). remote is matched across the whole country of the location, the others within the radius. ["remote"] is the same search as remote: true.
bonuses_onlyNoAdvanced filter: only jobs that state a bonus (sign-on, performance, referral, commission and the like).
hiring_brandNoFilter: one brand inside the company, for example company "Google" with hiring_brand "YouTube"; used only together with company.
salary_floorNoAdvanced filter: minimum annualized salary in USD; a posting qualifies when the lower bound of its pay band reaches the floor. Jobs without a USD salary are dropped.
strict_remoteNoAdvanced filter: only postings checked as fully remote that can be worked from the requested location: the posting names that area, allows anywhere, or does not say where. Stricter than remote; work_modes other than remote do not apply with it.
posted_days_agoNoNumber of days ago to search for jobs (1-365)
employment_typesNoFilter: jobs offered as any of these employment types (full_time, part_time, contractor, temporary, intern, volunteer, per_diem, other).
hide_low_qualityNoAdvanced filter: hides postings with a risky ghost grade (D/F); ungraded postings stay.
exclude_companiesNoAdvanced filter: official company names whose jobs are removed from the results, across every job board each employer posts on.
experience_levelsNoFilter: jobs at any of these experience levels (entry_level, mid_level, senior_level, executive). The level comes from the years of experience the posting asks for and the seniority in its title, the higher of the two; entry_level never includes a posting asking for more than two years.
h1b_sponsors_onlyNoAdvanced filter: only companies known to sponsor H1B visas.
confirmed_work_fromNoAdvanced filter: with strict_remote, also leaves out postings that do not say where the work can be done from.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
jobsNo
previewNo
feedKindNo
feedStatusNo
continueUrlNo
jobSearchIdNo
resultSetIdNo
statusOrderNo
revalidatingNo
resultBatchIdNo
trackerWebUrlNo
profileSetupUrlNo
profileSetupStateNo
lowRelevanceNoticeNo
system_instructionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed30 schema fields changedv1.1.16
    • addedInput schema / properties / benefits
      Added value: +{
      +  "description": "Advanced filter: benefit names such as \"health insurance\", \"401k\" or \"parental leave\"; a job qualifies only when it states every listed benefit. Names that match no known benefit are ignored.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 10,
      +  "type": "array"
      +}
    • addedInput schema / properties / bonuses_only
      Added value: +{
      +  "description": "Advanced filter: only jobs that state a bonus (sign-on, performance, referral, commission and the like).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / companies
      Added value: +{
      +  "description": "Filter: official company names; a job from any of them qualifies, across every job board each employer posts on. More than one company makes it an advanced filter. Next to company, a job has to match both; hiring_brand narrows company only.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 20,
      +  "type": "array"
      +}
    • addedInput schema / properties / confirmed_work_from
      Added value: +{
      +  "description": "Advanced filter: with strict_remote, also leaves out postings that do not say where the work can be done from.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / education
      Added value: +{
      +  "description": "Filter: jobs whose posting requires one of these education levels (no_requirements, high_school, associate_degree, bachelor_degree, professional_certificate, postgraduate_degree); bachelor_degree means the posting asks for a bachelor degree, not that it suits someone holding one.",
      +  "items": {
      +    "enum": [
      +      "no_requirements",
      +      "high_school",
      +      "associate_degree",
      +      "bachelor_degree",
      +      "professional_certificate",
      +      "postgraduate_degree"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / employment_types
      Added value: +{
      +  "description": "Filter: jobs offered as any of these employment types (full_time, part_time, contractor, temporary, intern, volunteer, per_diem, other).",
      +  "items": {
      +    "enum": [
      +      "full_time",
      +      "part_time",
      +      "contractor",
      +      "temporary",
      +      "intern",
      +      "volunteer",
      +      "per_diem",
      +      "other"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / exclude_companies
      Added value: +{
      +  "description": "Advanced filter: official company names whose jobs are removed from the results, across every job board each employer posts on.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 20,
      +  "type": "array"
      +}
    • addedInput schema / properties / experience_levels
      Added value: +{
      +  "description": "Filter: jobs at any of these experience levels (entry_level, mid_level, senior_level, executive). The level comes from the years of experience the posting asks for and the seniority in its title, the higher of the two; entry_level never includes a posting asking for more than two years.",
      +  "items": {
      +    "enum": [
      +      "entry_level",
      +      "mid_level",
      +      "senior_level",
      +      "executive"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / hiring_brand
      Added value: +{
      +  "description": "Filter: one brand inside the company, for example company \"Google\" with hiring_brand \"YouTube\"; used only together with company.",
      +  "type": "string"
      +}
    • changedInput schema / properties / min_match / description
      Previous value: -"Advanced filter: minimum personal FoundRole match score (0-100); needs a resume on the account."New value: +"Advanced filter: lowest personal FoundRole match grade to keep, the same letter each job shows in insights.match.grade. A and A- are rare even for a strong resume; B keeps good and strong matches; C+ also keeps fair ones. Needs a resume on the account."
    • addedInput schema / properties / min_match / enum
      Added value: +[
      +  "A",
      +  "A-",
      +  "B+",
      +  "B",
      +  "B-",
      +  "C+",
      +  "C"
      +]
    • removedInput schema / properties / min_match / maximum
      Removed value: -100
    • removedInput schema / properties / min_match / minimum
      Removed value: -0
    • changedInput schema / properties / min_match / type
      Previous value: -"integer"New value: +"string"
    • addedInput schema / properties / radius
      Added value: +{
      +  "description": "Search radius in miles around a city location (default 40); not used for state, country or remote searches.",
      +  "maximum": 100,
      +  "minimum": 5,
      +  "type": "integer"
      +}
    • changedInput schema / properties / remote / description
      Previous value: -"Advanced filter: only remote-eligible jobs (respects the location/region scope)."New value: +"Advanced filter: only remote-eligible jobs, matched across the whole country of the requested location rather than its radius."
    • changedInput schema / properties / salary_floor / description
      Previous value: -"Advanced filter: minimum annualized salary in USD; a posting qualifies when the midpoint of its pay band reaches the floor. Jobs without salary data are dropped."New value: +"Advanced filter: minimum annualized salary in USD; a posting qualifies when the lower bound of its pay band reaches the floor. Jobs without a USD salary are dropped."
    • addedInput schema / properties / sort
      Added value: +{
      +  "description": "Result order (score, posted_at, match, salary): score is relevance and the default, posted_at is newest first, salary is highest pay first, match is best personal fit first and needs a resume. Ordering by salary or match is an advanced option.",
      +  "enum": [
      +    "score",
      +    "posted_at",
      +    "match",
      +    "salary"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / strict_remote
      Added value: +{
      +  "description": "Advanced filter: only postings checked as fully remote that can be worked from the requested location: the posting names that area, allows anywhere, or does not say where. Stricter than remote; work_modes other than remote do not apply with it.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / work_modes
      Added value: +{
      +  "description": "Advanced filter: jobs in any of these work modes (on_site, remote, hybrid). remote is matched across the whole country of the location, the others within the radius. [\"remote\"] is the same search as remote: true.",
      +  "items": {
      +    "enum": [
      +      "on_site",
      +      "remote",
      +      "hybrid"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / continueUrl
      Added value: +{
      +  "type": "string"
      +}
    • removedOutput schema / properties / jobs / items / properties / estimatedSalary / properties / basedOn
      Removed value: -{
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • addedOutput schema / properties / jobs / items / properties / estimatedSalary / properties / currency
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / jobs / items / properties / related
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / jobs / items / properties / resultItemId
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / preview
      Added value: +{
      +  "properties": {
      +    "continueUrl": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "hidden": {
      +      "type": "integer"
      +    },
      +    "hiddenAtLeast": {
      +      "type": "boolean"
      +    },
      +    "shown": {
      +      "type": "integer"
      +    }
      +  },
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • removedOutput schema / properties / proFilterUpsellUrl
      Removed value: -{
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • addedOutput schema / properties / resultBatchId
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / resultSetId
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / system_instruction
      Added value: +{
      +  "type": "string"
      +}
  2. First observedv1.1.9

TDQS

A4.8/5.0
Behavior5/5

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

Annotations carry only readOnlyHint/openWorldHint/destructiveHint, so the description does the heavy lifting: it discloses pagination via nextCursor and the cursor-only protocol, entitlements-gated result truncation for non-Pro accounts, profile-driven personalization, strict_remote vs remote semantics, and that constraints left out of the call are simply not applied. This is far beyond what the annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is valuable but the middle and later paragraphs largely restate semantics already encoded in the 100%-covered schema (work_modes vs remote independence, strict_remote/confirmed_work_from, the advanced-filter list), producing a dense wall of text with meaningful redundancy. Front-loading is good, but several sentences do not earn their place against the schema.

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 23-parameter, zero-required search tool with an output schema, the description covers the remaining unknowns an agent needs: profile/entitlement behavior, pagination protocol, the id-to-jobs_details handoff, and the fact that omitted constraints are not applied. Return-value explanation is correctly delegated to the output schema.

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?

Schema coverage is 100%, yet the description still adds mapping value by translating natural-language constraints (remote-only work, H1B sponsorship, salary floor, hiding risky postings) onto the exact parameter names remote, h1b_sponsors_only, salary_floor, hide_low_quality, min_match, and by noting sort only when ordering by salary/match and companies only for multiple employers.

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 opening sentence states a specific verb and resource — 'Searches a database for real-time job listings' — and the rest of the description makes clear how it differs from jobs_recommendations, jobs_details, and jobs_analyze_external. An agent can select it without opening any sibling 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?

Explicit routing rules: use jobs_details with a result's `id`/`resultItemId` for full posting text; an omitted or profession-matching query falls into the same personalized feed as jobs_recommendations; a different profession falls back to general search. It also states when advanced filters apply and what happens without Pro.

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