Skip to main content
Glama
Panda Federation Tools

Panda Federation Tools

H-1B LCA Visa Sponsor Leads: DOL Employers, Jobs & Wages

h1b_lca_sponsor_leads
Read-only

Find employers sponsoring H-1B, H-1B1, or E-3 workers from Department of Labor LCA disclosure data, then filter by employer, location, job title, SOC code, wage, or date and export sponsor lists.

Instructions

Find employers sponsoring H-1B, H-1B1 and E-3 workers from the US Department of Labor OFLC LCA disclosure data (FY2026 Q3 default), with job title, SOC code, worksite, wage range and unit, case status, dates and worker count, plus a free employer roll-up sheet. Unlike npi_provider_lists (healthcare providers) and federal_contract_finder (federal awards), this is labor-condition-application filings. Use when recruiters, immigration attorneys, payroll/benefits/relocation sellers or wage analysts need sponsor lists by employer, state, city, title or SOC. Do not use for approved-visa outcomes, individual workers or non-LCA visas (PERM, O-1). Parameters: employers, states, cities, titleContains, socContains narrow rows; visaClass defaults H-1B (All widens it); caseStatuses, minWage with wageUnit, receivedFrom/To or daysBack filter further; fiscalYearQuarter or dataUrl pick another disclosure file; demoMode (or empty input) returns a tiny embedded sample without the ~250 MB DOL download; maxResults caps billed cases (hard max 5000). Tight filters finish faster. Runs with no matches are free. Returns per item: agentSummary, caseNumber, status, receivedDate, visaClass, employerName, employerCity, employerState, jobTitle, socCode, socTitle, worksiteCity, worksiteState plus wage, date and worker-count fields; plus LCA_CASES_XLSX (Cases + Employers sheets)/CSV.

Behavior: read-only; runs the Apify Actor pandadad0214/h1b-lca-sponsor-leads (https://apify.com/pandadad0214/h1b-lca-sponsor-leads) on your own Apify account. Price: $0.002 per lca case returned. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

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": "h1b_lca_sponsor_leads"
  }
}

Input Schema

NameRequiredDescriptionDefault
citiesNoWorksite cities. Worksite city substring match, e.g. Austin, Seattle.
statesNoWorksite states. 2-letter worksite state codes, e.g. TX, CA, NY.
dataUrlNoCustom disclosure file URL. Optional full URL to an LCA_Disclosure_Data_*.xlsx. Overrides fiscal year / quarter.
minWageNoMinimum wage (from rate). Keep cases whose wage-from is at least this amount (same unit as Wage unit).
daysBackNoReceived in the last N days. Optional; ignored when Received from is set. Uses decision/received date when available.
demoModeNoDemo mode (embedded sample). Use the tiny embedded sample instead of downloading the ~250 MB DOL file. For empty-input demos and offline tests only.
wageUnitNoWage unit. Only keep this pay unit (Year, Hour, Month, Week, Bi-Weekly). Empty = any. Choices: = Any; Year = Year; Hour = Hour; Month = Month; Week = Week; Bi-Weekly = Bi-Weekly.
employersNoEmployer name contains. Substring match on employer name (any). e.g. Google, Infosys, Deloitte.
visaClassNoVisa class. Default H-1B. Choose All to include H-1B1 and E-3. Choices: H-1B = H-1B; H-1B1 Chile = H-1B1 Chile; H-1B1 Singapore = H-1B1 Singapore; E-3 Australian = E-3 Australian; All = All (H-1B + H-1B1 + E-3).H-1B
maxResultsNoMaximum results. You pay per LCA case returned, so this also caps the cost. Default 200 (hard max 5000).
receivedToNoReceived on or before. Optional YYYY-MM-DD.
socContainsNoSOC code or title contains. Match SOC_CODE or SOC_TITLE, e.g. 15-1252, Software Developers.
caseStatusesNoCase statuses. Default: Certified. Add Certified - Withdrawn if useful.
onlyFullTimeNoFull-time positions only. Skip part-time LCAs.
receivedFromNoReceived on or after. Optional YYYY-MM-DD.
run_max_itemsNoOptional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
titleContainsNoJob title contains. Substring match on job title, e.g. software, data scientist, nurse.
run_timeout_secsNoOptional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
fiscalYearQuarterNoFiscal year / quarter file. Optional override of the DOL filename stem, e.g. FY2026_Q3 or FY2025_Q4. Default = latest known (FY2026_Q3).
run_max_charge_usdNoOptional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered, yet the description adds substantial operational context: the underlying Actor, $0.002 per case pricing, run_max_charge_usd cap, run_max_items default, 5-15 s typical latency, 300 s timeout ceiling, and no-charge-on-empty-runs. The only notable gap is that return-format detail is partly redundant with the field list rather than explaining truncation semantics beyond the one clause.

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 and sibling differentiation are front-loaded, then filters, then billing/behavior, which is a sensible order for a 20-parameter tool. It is dense and long, with some restatement of schema-level filter details (titleContains, socContains, wageUnit) that the schema already carries.

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 20-parameter, zero-required, no-output-schema tool, the definition covers data source, default quarter, filter semantics, demo fallback, cost model and caps, timeout behavior, and the returned item fields. Nothing an agent needs in order to call it safely or predict cost 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, but the description earns extra credit by documenting non-obvious cross-parameter interactions the schema cannot express: run_max_items fills maxResults when unset and therefore governs billing, and 'setting maxResults higher can bill more than is returned.' It also clarifies that visaClass 'All' widens results and that daysBack is superseded by receivedFrom.

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: 'Find employers sponsoring H-1B, H-1B1 and E-3 workers from the US Department of Labor OFLC LCA disclosure data', plus the fields returned. It explicitly contrasts itself with npi_provider_lists (healthcare providers) and federal_contract_finder (federal awards), so an agent can route without opening schemas.

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?

Names concrete consumer personas ('recruiters, immigration attorneys, payroll/benefits/relocation sellers or wage analysts') and the dimensions to query by, then gives explicit exclusions: 'Do not use for approved-visa outcomes, individual workers or non-LCA visas (PERM, O-1).' It also says when to use demoMode and that tight filters finish faster.

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