Skip to main content
Glama

New York New Business Leads: New DOS Filings

new_york_new_business_leads
Read-only

Lists newly filed New York LLCs and corporations from NY Department of State data, filtered by county, city, ZIP, entity type or filing date, to find new business owners for outreach.

Instructions

List newly filed New York LLCs, corporations and other entities from the official NY Department of State Active Corporations open data (data.ny.gov), with DOS ID, entity type, filing date, county, jurisdiction, process name and address, and CEO and registered agent when filed. Unlike florida_new_business_leads (Sunbiz filings with officers) and texas_new_business_leads (Comptroller franchise taxpayers), this is New York DOS filings. Use when banks, payroll, insurance, accounting, agencies or suppliers want new New York owners in their first weeks. Do not use for other states, for emails or phones (the source has none) or for sole proprietors. Parameters: daysBack (default 7) or filedFrom/filedTo set the window; counties, cities, zipPrefixes, entityTypes (e.g. DOMESTIC LIMITED LIABILITY COMPANY) and nameContains narrow rows; requireCeo and requireProcessAddress drop incomplete rows (CEO is often empty on new LLCs, so the process address is the reliable contact); maxResults caps billed businesses. Runs with no matches are free. Returns per item: agentSummary, dosId, name, entityType, filingDate, county, jurisdiction, processName, processAddress, processCity, processState, processZip, ceoName and CEO address fields, sourceUrl; plus NYBIZ_XLSX/CSV.

Behavior: read-only; runs the Apify Actor pandadad0214/new-york-new-business-leads (https://apify.com/pandadad0214/new-york-new-business-leads) on your own Apify account. Price: $0.0015 per business 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": "new_york_new_business_leads"
  }
}

Input Schema

NameRequiredDescriptionDefault
citiesNoCities. Match DOS process city OR location city (case-insensitive), e.g. New York, Brooklyn, Queens, Buffalo, Rochester, Albany.
filedToNoFiled on or before. Optional YYYY-MM-DD; overrides days back when set with Filed on or after.
countiesNoCounties. NYS county of the entity, e.g. New York (Manhattan), Kings (Brooklyn), Queens, Bronx, Richmond (Staten Island), Suffolk, Nassau, Westchester, Erie, Monroe.
daysBackNoFiled with DOS in the last N days. Default 7. Matches initial DOS filing date. Use 1 on a daily schedule.
filedFromNoFiled on or after. Optional YYYY-MM-DD; overrides days back. Applied to initial DOS filing date.
maxResultsNoMaximum results. You pay per business returned, so this also caps the cost. Default 500; hard max 5000.
requireCeoNoOnly with a CEO name on file. Keep rows that list a CEO (dataset field CEO Name / chairman_name). Brand-new LLCs often have no CEO on file yet.
entityTypesNoEntity types. Empty = all types. The open dataset includes domestic and foreign LLCs, corporations, nonprofits, professional entities and partnerships — not only corporations.
zipPrefixesNoZIP prefixes. Match DOS process ZIP or location ZIP starts-with, e.g. 100 (Manhattan), 112 (Brooklyn), 113 (Queens), 104 (Bronx), 103 (Staten Island), 117 (Suffolk).
nameContainsNoName contains. Case-insensitive substring of the current entity name, e.g. construction, realty, consulting.
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.
run_timeout_secsNoOptional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
run_max_charge_usdNoOptional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
requireProcessAddressNoOnly with a DOS process address. Keep rows that list a DOS process street address (the reliable contact address in this source).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover read-only/open-world, but the description adds what annotations cannot: $0.0015 per returned business, free runs on zero matches, run_max_charge_usd default $0.50 cap, runtime expectations (5-15 s typical, minutes for large crawls, max 300 s), and the interaction where run_max_items fills maxResults when unset and can bill more than returned. This is materially useful cost and failure-mode context.

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-loaded with purpose, then differentiation, then usage, then parameters, then behavior/pricing — a sensible order. It is long and the parameter paragraph is dense to the point of skimming, but nearly every clause carries operational information rather than filler.

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 14-parameter, no-output-schema, paid-actor tool, the description covers cost model, return shape (agentSummary, dosId, name, filingDate, ... sourceUrl plus XLSX/CSV), timeout recovery guidance, and the {actor, count, items} envelope. Nothing an agent needs to call it correctly or budget for it 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 baseline is 3, but the description adds real meaning: the daysBack vs filedFrom/filedTo override relationship, the filter-versus-narrow grouping of counties/cities/zipPrefixes/entityTypes/nameContains, and the practical note that requireCeo drops many new LLCs while requireProcessAddress is the reliable contact. Only minor duplication of schema defaults keeps it off a 5.

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+resource (list newly filed NY LLCs/corporations/other entities from NY DOS open data) and enumerates the returned fields. It explicitly distinguishes itself from the named siblings florida_new_business_leads (officers) and texas_new_business_leads (franchise taxpayers), so an agent can route without opening another 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?

Gives an explicit positive use case (banks, payroll, insurance, accounting, agencies, suppliers targeting new NY owners in their first weeks) and explicit exclusions (other states, emails/phones the source lacks, sole proprietors). The alternatives are named with the reason each differs, not merely listed.

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