`search_industries_naics_sic` next channel

Status: Modified (migrated to the production data-api/v2 endpoint with Authorization: Bearer auth; description trimmed to ≤1,700 chars so it renders in full on the deployed connector, plus an explicit product-category boundary. Parameters, output shape, and cost are unchanged.) This tool is on the private next MCP channel for allow-listed orgs. When promoted, this file moves to mcp-tools/search-industries-naics-sic.md.

Search and translate industry codes across HG industry (23 buckets), NAICS 2012 (~2,200 codes), and SIC 1987 (~1,500 codes) in a single call. This tool searches taxonomy definitions, not company records — do NOT use it to find what industry a specific company belongs to (call company_firmographic for that), and do NOT use it for technology/product categories like "IaaS", "CRM", or "cloud infrastructure" (use get_product_category for those). Colloquial sector terms (fintech, saas, cybersecurity, etc.) are expanded server-side; the response's alias_expansions field shows what ran. Pass returned industry_id values to search_companies and use sic.sic_standard_code (not sic.sic_code) when chaining SIC codes downstream.

Integration required: hginsights_v2__data_api Cache schema version: 2 (differs from base — stale cached payloads from the public channel will not be served)

Parameters

Parameter	Type	Required	Default	Description
`q`	`string`	Optional	—	Text input → case-insensitive substring match against industry/NAICS/SIC name columns. All-digit input → prefix match against code columns only (e.g. `q=52` returns NAICS sector 52 and its descendants, not codes that merely contain "52" like 1152). Multi-term: comma-separated (`software,publishing,saas`) runs the union (OR). Colloquial terms (fintech, saas, healthcare, cleantech, ev, cybersecurity, …) are expanded server-side; the response's `alias_expansions` shows what ran. Minimum 2 characters.
`taxonomy`	`enum` (`industry` \| `naics` \| `sic`)	Optional	—	Restricts matching to one taxonomy AND groups results by its primary key — one row per distinct entity with crosswalk counts on the matched block. Other blocks become `{}`.
`naics_leaf_only`	`boolean`	Optional	`false`	Only meaningful when `taxonomy=naics`. When true, drops 2/3/4/5-digit NAICS rollup codes and returns only the 6-digit leaf codes (1,590 of 2,209). Useful when chaining results into endpoints that expect specific industry codes. Silently ignored for other taxonomies.
`limit`	`integer`	Optional	`50`	Page size, 1–500.
`offset`	`integer`	Optional	`0`	Page offset, ≥ 0.

Response Format

{
  "results": [
    {
      "matched_on": "naics",
      "industry": {},
      "naics": {
        "naics_code": "541511",
        "naics_name": "Custom Computer Programming Services",
        "naics_top_parent_code": "54",
        "naics_top_parent_name": "Professional, Scientific and Technical Services",
        "hierarchy_level": "national_industry",
        "is_leaf": true,
        "display_name_with_level": "Custom Computer Programming Services (national_industry 541511)",
        "sic_count": 1
      },
      "sic": {
        "sic_code": "I7371",
        "sic_standard_code": "7371",
        "sic_name": "Computer Programming Services",
        "is_hg_extension": true,
        "naics_count": 3
      }
    }
  ],
  "pagination": {
    "total": 1,
    "limit": 50,
    "offset": 0,
    "has_more": false,
    "total_pages": 1,
    "offset_exceeds_total": false
  },
  "alias_expansions": [
    { "term": "saas", "expanded_to": ["software publishers", "computer programming"] }
  ],
  "suggestions": []
}

Response fields

Field	Meaning
`results`	Crosswalk rows. In unscoped mode, one row per match across taxonomies. In grouped mode (`taxonomy` set), one row per distinct entity in the requested taxonomy.
`results[].matched_on`	Which taxonomy produced the match (`industry` \| `naics` \| `sic`). Present when `q` is set.
`results[].industry`	HG industry block; `{}` when not the matched/populated taxonomy. Contains `industry_id`, `industry_name`, and (grouped mode only) `naics_count`, `sic_count`.
`results[].naics`	NAICS 2012 block; `{}` when not the matched/populated taxonomy. Contains `naics_code`, `naics_name`, `naics_top_parent_code`, `naics_top_parent_name`, `hierarchy_level`, `is_leaf`, `display_name_with_level`, and (grouped mode only) `sic_count`.
`results[].naics.hierarchy_level`	NAICS level derived from code length: `sector` \| `subsector` \| `industry_group` \| `naics_industry` \| `national_industry`.
`results[].naics.is_leaf`	True iff `hierarchy_level == "national_industry"`. Only leaves are safe to chain into downstream code-based filters.
`results[].sic`	SIC 1987 block; `{}` when not the matched/populated taxonomy. Contains `sic_code`, `sic_standard_code`, `sic_name`, `is_hg_extension`, and (grouped mode only) `naics_count`.
`results[].sic.sic_standard_code`	Standard SIC-1987 code (e.g. `"7372"`) — the value to pass to downstream APIs. Empty for sector-level rows.
`results[].sic.sic_code`	HG-extended SIC code with an internal letter prefix (e.g. `"I7372"`). Do NOT pass to downstream APIs — use `sic_standard_code`.
`pagination.total`	Total rows matching the filter (not just this page).
`pagination.total_pages`	`ceil(total / limit)`.
`pagination.offset_exceeds_total`	True when `offset >= total` and `total > 0` — diagnostic for paging-past-end.
`alias_expansions`	Present only when one or more `q` terms were rewritten server-side. Each entry shows the colloquial `term` and the substrings it `expanded_to`.
`suggestions`	Present only when `results` is empty AND `q` contained a text term. Up to 5 closest taxonomy names by trigram distance — use to self-heal typos / near-misses before retrying.

Example Usage

{
  "tool": "search_industries_naics_sic",
  "parameters": {
    "q": "541511"
  }
}

get_product_category — use this for technology/product categories ("IaaS", "CRM", "cloud infrastructure"), NOT this industry-taxonomy tool.
company_firmographic — find what industry a specific company belongs to (pass companyDomain or hg_id).
search_companies — pass returned industry_id values to the industry_ids parameter to filter companies by industry.

Changelog

2026-08-12 — Description truncation fix + product-category boundary (PR 1/2)

Availability: live on next only (allow-listed orgs via POST /api/mcp/next). This entry graduates to the public channel when promoted in PR 2/2.

Why this changed: A live audit found the tool description exceeded the ~2,048-char limit the deployed connector enforces, so ToolSearch was truncating it. The audit also found two-way selection ambiguity: a model could reach for this industry-taxonomy tool when it actually wanted a technology/product category (IaaS, CRM, cloud infrastructure), which HG serves through get_product_category.

What changed

Description trimmed to ≤1,700 chars. The description was condensed so it renders in full on the deployed connector, preserving the taxonomy coverage note, use-case list, alias-expansion behavior, zero-result suggestion rules, NAICS hierarchy guidance, and the corrected ~1,065 leaf-code count.
Added an explicit product-category boundary. The description now states to NOT use this tool for technology/product categories ("IaaS", "CRM", "cloud infrastructure") and to use get_product_category instead — this tool searches NAICS/SIC/HG industry taxonomy definitions, not product categories.

What stayed the same

All parameters (q, taxonomy, naics_leaf_only, limit, offset, …) are unchanged.
Output shape (results, alias_expansions, suggestions, hierarchy fields, …) is unchanged.
Tool key (search_industries_naics_sic), the free credit cost (0), and the upstream are identical to v1.

The cache schema version is bumped to super.getCacheSchemaVersion() + 1 (required by the manifest invariant even for a description-only override).

Parameters​

Response Format​

Response fields​

Example Usage​

Related Tools​

Changelog​

2026-08-12 — Description truncation fix + product-category boundary (PR 1/2)​

What changed​

What stayed the same​