Skip to main content
Glama

CoreLoop Business Network

search_businesses

Read-only

Search the CoreLoop business directory. Start here: every other tool on this endpoint needs a business, and each result carries the business_id and slug you pass to them as the business argument. business_id is a PUBLIC, OPAQUE, STABLE routing identifier: it is safe to store and re-use across sessions, it stays the same when a business renames itself or changes its slug, and it carries no sensitive information. Treat it as a token — do not parse it, do not derive meaning from its format, and do not construct one. Pass back exactly the value you were given. A result with asserts_no_physical_location: true has stated that it has no premises (consultants, trades, online-only) — it is intentionally absent from city search rather than missing data. false means no such statement was made; it does NOT imply premises. Results are returned in your requested language when the business has published a translation: send ?locale=<code> on the endpoint URL (takes precedence) or an Accept-Language header. Each result reports the language it is written in (locale), the business's original language (content_locale), and every language it is available in (available_locales). mcp_url, a2a_url and page_url — and every URL inside protocol_urls — are null when that surface is currently switched off for the business: a null is intentional (do not construct the URL yourself), and the business remains reachable through its non-null surfaces. data_source: "directory" marks these rows as the search projection; call get_business_info for the live profile. PAGING: one call returns at most limit results. Read has_more — a short page is not proof of the end — and pass next_cursor back as cursor for the next page. The cursor is opaque and bound to the filters and sort it was issued for: change any of them and it is rejected, so start a new search instead. limit may change between pages.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cityNoFilter by city (case-insensitive exact match)
limitNoMaximum results per page (1-20). Out-of-range values are clamped, not rejected.
queryNoSearch query (business name or keyword)
cursorNoContinuation token from a previous response's `next_cursor`. Omit for the first page. It is opaque and bound to the filters and sort it was issued for: pass it back byte-for-byte, and change nothing except `limit` between pages — any other change makes it invalid and you must start a new search. At most 100 results are reachable by paging; narrow the filters to see beyond that.
sort_byNoSort results. Default: relevance
categoryNoFilter by business category (case-insensitive exact match). Canonical categories: Accounting & Tax, Agriculture & Farming, Automotive, Beauty & Wellness, Childcare & Family, Cleaning Services, Construction & Renovation, Creative & Arts, Education & Training, Events & Entertainment, Financial Services, Fitness & Sports, Food & Beverage, Funeral & Memorial, Health & Medical, Home Services, Legal Services, Media & Photography, Nonprofit & Community, Personal Care & Therapy, Pets & Animals, Professional Services, Real Estate, Religious & Spiritual, Retail & Shopping, Security Services, Sports & Recreation, Technology & IT, Transportation & Logistics, Travel & Tourism, Other
min_ratingNoMinimum average rating (0-5)
capabilitiesNoFilter by capability tags (e.g. real_time_booking, live_pricing, verified)
service_typeNoFilter by service type keyword
verified_onlyNoOnly show verified businesses
has_live_bookingNoOnly show businesses with real-time booking
has_live_catalogNoOnly show businesses with live catalog pricing

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
has_moreNoTrue when more results exist beyond this page. Read this rather than inferring from `returned_count`: a short page is not proof of the end.
businessesNo
next_cursorNoOpaque continuation token, or null on the last page. Pass it back unchanged as `cursor` to get the next page. It is bound to this search's filters and sort — change them and it is rejected, so start a new search instead. Do not parse, modify or construct one.
returned_countNo
requested_localeNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden. It thoroughly discloses behavior: null URL semantics (do not construct yourself), asserts_no_physical_location meaning, locale/language behavior, cursor binding to filters, limit clamping, data_source meaning, and the 100-result paging limit. This is exceptionally comprehensive.

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 thorough and covers critical details (ID safety, language, paging, availability). It is dense but front-loaded with the purpose. Though long, every sentence adds value; the only minor deduction is that the length might be overwhelming, but it's structured logically.

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?

Given the 10 parametersaging rules, language behavior, and null semantics, the description covers everything needed for correct use. The output schema is not provided but the description explains key result fields (business_id, slug, asserts_no_physical_location, locale fields). Complete for a complex search tool.

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?

The description complements well the schema by explaining the `business_id` token semanticscars (public, opaque, stable), the cursor binding rules, and the meaning of nulls. However, it doesn't deeply elaborate on each parameter beyond what the schema provides—the schema already covers the fields well, so the baseline is 3 and the added context on business_id and cursor pushes it to 4.

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 description clearly states the tool searches the CoreLoop business directory must start here and explicitly mentions that each result carries the business_id and slug needed by other tools. It distinguishes this from other tools by positioning it as the entry point that returns identifiers used elsewhere.

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?

Provides explicit guidance on when to use this tool (start here since every other tool needs a business), explains the importance of business_id, and even mentions alternative surfaces (get_business_info for live profile). The paging instructions with has_more and next_cursor are clear usage directives.

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