Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

datasets_starbucks_stores_search

Find Starbucks stores worldwide using full-text, city, or location filters. Access details like address, phone, weekly hours, and amenity codes for each store.

Instructions

Search the Starbucks store directory. Searches the worldwide Starbucks store directory (dataset id starbucks-stores), built by grid-tiling the store locator around its 50-result cap. Each store has its store number, name, phone, full address, coordinates, weekly hours, amenity codes, and pick-up options. Store discovery is global, but hours, amenities, and phone numbers are populated per market and are largely absent outside the US, Canada, Europe, and the Gulf; an empty schedule means "not published for this market", not "closed". country is the store's true country while market is crawl provenance (the US host geocodes worldwide). Supports full-text q, country/state/city/market/amenity filters, lat/lon/radius_m radius filtering, and sort (relevance, distance_asc).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFull-text search over store name, city, and address, max 256 characters
latNoLatitude for radius filtering or distance sort, requires lon
lonNoLongitude for radius filtering or distance sort, requires lat
cityNoExact city filter
pageNoPage number, defaults to 1
sortNoSort enum: relevance, distance_asc
stateNoState/region code filter, e.g. WA
marketNoCrawl-provenance market filter. One of: us, ca
amenityNoAmenity code filter, e.g. DT (Drive-Thru), XO (Mobile Order and Pay)
countryNoISO-3166-1 alpha-2 country filter, e.g. US, GB, JP
radius_mNoRadius in meters, 1 through 50000; requires lat and lon
page_sizeNoPage size, defaults to 20 and maxes at 100; page * page_size must be <= 10000

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.16.2

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden, and it does so thoroughly. It discloses local data limitations (hours/phone/amenities absent outside the US, Canada, Europe, and the Gulf), clarifies that an empty schedule means 'not published', and differentiates `market` as crawl provenance from `country` as true geography. It also explains the grid-tiling methodology and its 50-result cap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence earns its place: purpose holds first, dataset context follows, then field coverage, then market caveats, then the country/market semantics, then the supported filter list. It is compact despite covering a 12-parameter tool and multiple data caveats, with no filler or repetition of schema text.

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 tool with 12 optional parameters and no output schema, this description is unusually complete. It explains what results contain, the geographic coverage of data, the meaning of empty fields, filter and sort categories, and the construction limitation. It gives an agent enough context to call the tool and correctly interpret results without further lookups.

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 input schema already has 100% description coverage, so the baseline is 3. The description adds real value by distinguishing `country` from `market`, and by summarizing the filter and sort groups. Most of the other filter mentions merely echo the schema, but the market/country distinction is unique and corrects a potential misinterpretation.

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 opens with a clear verb-resource pair: 'Search the Starbucks store directory' and explicitly names the dataset id. It further distinguishes itself from sibling tools (facets, item, nearby) by describing the full-text, filter, and sort capabilities, and even explains the grid-tiling construction around a 50-result cap.

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 clearly implies when to use the tool: any time you need to search the Starbucks store directory with free text, filters, or radius, and it explains the available filters and sort options. However, it never explicitly mentions alternative sibling tools or states when another tool should be used, so no exclusions are provided.

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

Install Server

Other Tools