within

Find boutiques in a city

boutique_directory

Read-onlyIdempotent

Find independent boutiques and clothing stores by city, neighbourhood, designer, shop type, or name, including stockists and where each shop sells on within.

Instructions

Independent boutiques and clothing stores in a city, from within's directory of about 8,700 shops in more than 140 cities. Each shop comes with the kind of shop it is, its street and neighbourhood, a few designers it stocks, its page on shopwithin.co, and whether it sells on within. Use this when someone asks for clothing stores or boutiques in a city or neighbourhood, for luxury boutiques, for vintage, consignment or sneaker stores, for the stores that stock a designer (stockists) in a city or country, or for a shop by a word in its name. The list is A to Z, not ranked, with no ratings or reviews. Most shops in it do not sell on within. With no city it lists the cities covered.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "boutique_directory"
  }
}

Input Schema

Name	Required	Description
`city`	No	The city the shops are in, e.g. 'Toronto', 'New York', 'Melbourne': a place to shop, not the shopper's own location. A part of a city works too: 'Brooklyn'.
`kind`	No	The kind of shop, one of: vintage, consignment, archive, sneakers, streetwear, jewellery, watches, menswear, womenswear, concept.
`name`	No	A word in the shop's name, e.g. 'archive', 'kith'.
`limit`	No	Shops per page, default 12.
`offset`	No	Shops to skip; use next_offset from the page before.
`country`	No	A country name or two letter code, e.g. 'Australia', to search every city in it or to list its cities.
`designer`	No	A designer or brand the shop stocks, e.g. 'Diesel', 'Goyard', 'Zoe Kratzmann'.
`neighbourhood`	No	A neighbourhood in the city, e.g. 'Yorkville', 'SoHo', 'Le Marais'.

Output Schema

Name	Required	Description	Default
`note`	Yes
`kinds`	Yes
`place`	Yes
`total`	Yes
`cities`	Yes
`covered`	Yes
`view_url`	Yes
`boutiques`	Yes
`next_offset`	Yes
`neighbourhoods`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Nov 11, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: results are alphabetical rather than ranked, carry no ratings or reviews, and most listed shops do not sell on within — precisely the caveats an agent would otherwise misreport.

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-loads what the list is and what each record contains, then usage triggers, then the caveats (alphabetical, no ratings, mostly not sold on within). Dense and mostly waste-free, though the usage sentence is a long run-on list that could be tightened.

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 an 8-parameter, all-optional filtered directory search, it covers scope, filtering intents, sort order, data quality caveats, and the no-city fallback; an output schema exists so return shape needs no explanation, and annotations cover safety. Nothing needed to invoke it correctly is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not spell out: omitting city switches the tool to listing covered cities, and designer can be combined with a city or a country (stockists). Those are genuine semantic additions rather than restatements.

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?

States a specific verb+resource ('Independent boutiques and clothing stores in a city') and even quantifies the corpus (about 8,700 shops, 140+ cities) plus the fields each result carries. It is clearly distinguishable in content from piece- or brand-oriented siblings, though it never names how it differs from the similarly named list_boutiques.

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 a concrete when-to-use list: clothing stores or boutiques in a city/neighbourhood, luxury, vintage, consignment, sneakers, stockists of a designer, or a shop by name — and adds the fallback that with no city it lists covered cities. No explicit when-not or named alternative, so it stops short of a 5.

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