Skip to main content
Glama
Sign In
ScrapeBadger MCP Server

ScrapeBadger MCP Server

Official
by scrape-badger
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

yelp_search_businesses

Searches Yelp businesses by location, query, category, price and features, returning ratings, review counts, categories, addresses and opening hours, with sponsored listings kept separate.

Instructions

Search Yelp businesses for a location (US or Canada) in Yelp's own order, with rating, review count, categories, price, address and opening hours; sponsored listings come back separately in ads. Ten per page, pages 1-11. 15 credits per page with results; empty searches and errors are free. Follow next_page while has_next_page is true.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "location": "<location>"
    },
    "name": "yelp_search_businesses"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo1-based page, ten businesses each; pages 1-11.
priceNoComma-separated price levels 1-4 ($ to $$$$), e.g. 1,2.
queryNoWhat to search for (e.g. pizza, plumbers). Optional when category is set.
marketNoYelp site: us (www.yelp.com) or ca (www.yelp.ca).us
sort_byNoYelp's own result order.recommended
categoryNoYelp category alias, e.g. pizza, coffee, plumbing.
featuresNoComma-separated refinements: delivery, takeout, reservations, outdoor_seating, good_for_kids, dogs_allowed, free_wifi, wheelchair_accessible.
locationYesWhere to search, as typed into Yelp: city, neighbourhood, address or postcode.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden. It does well on several axes: sponsored results are returned separately in 'ads', pages are capped at 11 and hold ten results, and billing behavior is disclosed (charged per page with results, free for empty/error). It omits auth/prerequisite requirements and does not describe what an error response looks like, which are material gaps for an unannotated network-calling tool.

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?

Four front-loaded sentences: capability and returned fields first, then page size and limits, then cost, then the pagination loop. Every sentence carries information, though the middle sentences are telegraphic ('Ten per page, pages 1-11.') and repeat the page bounds already in the schema.

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?

With no output schema, the description usefully supplies the return shape (field list, separate ads array, next_page/has_next_page contract) and the cost model for an 8-parameter tool. The main residual gap is input requirements: the schema hints 'query is optional when category is set' but the description never states that at least one of query or category is effectively needed.

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 every parameter is already documented in the schema. The description only reinforces 'US or Canada' (market) and 'Yelp's own order' (sort_by default of recommended); it adds no syntax, format, or interaction rules (e.g., that query and category are individually optional but one is needed) beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

A specific verb and resource: 'Search Yelp businesses for a location (US or Canada)', plus an enumeration of the returned fields (rating, review count, categories, price, address, opening hours). An agent immediately knows this is the Yelp local-business search rather than a detail lookup. It does not explicitly contrast with the sibling yelp_list_markets, which is the only plausible confusion point.

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?

Gives clear operative guidance on pagination ('Follow next_page while has_next_page is true') and cost-driven usage ('15 credits per page with results; empty searches and errors are free'), which tells an agent to avoid speculative empty queries. It stops short of explicit when-not-to-use or naming an alternative tool, so it is context rather than 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