Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

datasets_bbb_businesses_search

Search BBB business profiles by name, category, city, state, rating, or accreditation. Returns grades, contact details, hours, and links to complaints and reviews.

Instructions

Search the BBB businesses dataset. Searches the BBB (Better Business Bureau) businesses index (dataset id enum value bbb-businesses) — business profiles crawled from bbb.org's own search/category-browse pages: computed A+-F letter-grade rating, paid-accreditation status, category, contact info, business details, operating hours, and products/services. Complaints, full reviews, and the full "reasons for rating"/service-area detail are NOT embedded here; each record instead carries complaints_url/reviews_url/more_info_url pointing at the live bbb-business-complaints/bbb-business-reviews/bbb-business-more-info endpoints for on-demand lookup. rating enum: A+, A, A-, B+, B, B-, C+, C, C-, D+, D, D-, F. sort enum: relevance, rating_desc, rating_asc, accredited_first, name_asc, years_in_business_desc.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFull-text match on the business name/category, max 256 characters
cityNoExact city filter, parsed from the profile URL
pageNoPage number, defaults to 1
sortNoSort enum: relevance, rating_desc, rating_asc, accredited_first, name_asc, years_in_business_desc
stateNoExact 2-letter state/province filter, parsed from the profile URL, e.g. tx
ratingNoExact letter-grade rating filter. Enum: A+, A, A-, B+, B, B-, C+, C, C-, D+, D, D-, F
run_idNoExact crawl run id filter
categoryNoExact category filter, e.g. Plumber. Use the values returned by facets?facet=category
page_sizeNoPage size, defaults to 20 and maxes at 100; page * page_size must be <= 10000
accreditedNoAccreditation filter; true keeps only accredited businesses
entity_typeNoExact entity-type filter, e.g. Limited Liability Company (LLC)
min_rating_rankNoNumeric floor against the denormalized rating rank (A+=12 down to F=0), e.g. 10 for 'A- and above'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.17.5
    • addedInput schema / properties / rating / enum
      Added value: +[
+  "A+",
+  "A",
+  "A-",
+  "B+",
+  "B",
+  "B-",
+  "C+",
+  "C",
+  "C-",
+  "D+",
+  "D",
+  "D-",
+  "F"
+]
    • addedInput schema / properties / sort / enum
      Added value: +[
+  "relevance",
+  "rating_desc",
+  "rating_asc",
+  "accredited_first",
+  "name_asc",
+  "years_in_business_desc"
+]
  2. Addedv1.16.0

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries full responsibility for behavioral disclosure. It states the data provenance (crawled from bbb.org search/category-browse pages), that ratings are computed and accreditation is paid, and explicitly lists what is NOT embedded in this endpoint. This goes well beyond a vague 'search' label and tells the agent what to expect from the records.

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 dense but purposeful, front-loading the search purpose and then covering provenance, embedded fields, exclusions, and enums. Every section earns its place, though the first two sentences are slightly redundant ('Search the BBB businesses dataset' followed by 'Searches the BBB ... index'). This minor repetition keeps it from a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with no output schema and no annotations, the description provides a strong mental model: what fields are embedded, what must be fetched on demand, the dataset id, and the enum ranges. It does not describe pagination metadata or result-level structure, but the schema already covers page/page_size and the description gives the agent enough context to call and interpret the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline of 3 applies. The description repeats the rating and sort enums but does not add meaning beyond what the schema already provides. There is no parameter explanation in the description that meaningfully supplements the schema, and none is needed because the schema is complete.

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?

Opens with 'Search the BBB businesses dataset,' a specific verb and resource. The description details what the records contain and explicitly states that complaints, full reviews, and reasons-for-rating detail are NOT embedded, which differentiates it from detail/on-demand siblings. It is not a tautology and gives an agent a precise idea of what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description tells the agent this is the index search and that complaints/reviews/more-info should be looked up on demand via the URLs carried on each record. It names the live endpoints rather than sibling tool names, but the exclusions and 'on-demand lookup' phrasing give clear decision context. It does not explicitly mention alternatives like facets or item endpoints, but provides enough guidance for correct routing.

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

Deploy Server

Other Tools