Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

starbucks_menu

Browse the full Starbucks menu for US or Canada, returning category trees and product details; add a store number to see item availability at that location.

Instructions

Browse the full Starbucks menu. Returns Starbucks' full menu as a category tree: top-level categories, their child categories, and every product with its product number, form, product type, sizes, default size, availability, and image. Pair a product's product_number and form with /starbucks/product to fetch full detail including nutrition. store_number optionally scopes the menu to one store, using a store number from /starbucks/stores; a store-scoped menu marks items that store does not carry with availability NotAvailableHere, while the unscoped menu reports everything as Available. market selects which country catalog to return, one of us or ca, defaulting to us; the two differ substantially (roughly 282 US products vs 253 CA, with exclusives on both sides). Only these two markets are available.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
marketNoStarbucks country site to read. One of: us, ca. Defaults to us
store_numberNoStarbucks store number to scope availability to, e.g. 101-54

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.5
    • addedInput schema / properties / market / enum
      Added value: +[
+  "us",
+  "ca"
+]
  2. Addedv1.16.2

TDQS

A4.9/5.0
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 and does so well: it discloses the return structure (categories, children, product fields), the availability semantics (store-scoped marks uncarried items NotAvailableHere vs unscoped reports everything Available), and market differences (us/ca product counts, exclusives, only two markets supported). This is unusually rich behavioral context.

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?

Front-loaded with purpose and structure of the response, then parameters. Every sentence is informative, though the density of clauses makes it longer than strictly necessary; still, little is wasted.

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?

With no output schema and no annotations, the description must explain both what is returned and how parameters behave. It does: it enumerates the returned fields, explains store-scoping and market selection, and links to the detail tool. Nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is already 100%, but the description goes beyond it by explaining where store_number comes from (/starbucks/stores) and its effect on availability, and by contrasting the us vs ca catalogs with approximate product counts and the note that only these two markets exist. This meaningfully enriches both parameters.

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?

States a specific verb+resource ('Browse the full Starbucks menu') and immediately specifies the return shape as a category tree with enumerated fields. This clearly distinguishes it from siblings like starbucks_product, starbucks_nutrition, and starbucks_nearest_store, and it even names the sibling it hands off to.

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?

Explicitly states when to use this (browse the whole menu) vs the alternative ('Pair a product's product_number and form with /starbucks/product to fetch full detail including nutrition'), and explains the conditional behavior of store_number and market. Both parameters come with clear selection guidance.

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