Skip to main content
Glama

Discover Stores and Supplier Apps

list_stores
Read-onlyIdempotent

[Store] [What it does] Lists connected seller stores with their application, country, currency, timezone and connection status, plus supplier applications and their connected accounts. Pass view=account_context to return only stores and supplier_apps; this view omits stores[].pricing_currency, stores[].shipping_profiles, and push_configuration. Omit view or use view=full for the full response. [When to use] Call it when the user asks which stores or supplier accounts are connected, about a store's currency, timezone or status, and proactively before any store-scoped action because downstream tools accept only a store ID. Trigger words: store list, supplier account, Shopify, store status, authorization, currency, timezone. [When not to use] For products inside a store use search_store_products; for pricing-rule detail use get_pricing_rule; for a reconnect link use start_store_reauthorization. It never adds, unbinds or edits stores or supplier accounts. [How to use]

  • In most cases, omit view and use the default full response. Pass view=account_context only when you need just stores and supplier apps/accounts without pricing, Shipping Profile, or product-push details.

  • Match the user's store reference against the returned stores; continue only on one clear match, ask the user to choose on multiple matches, and never write to all stores by default.

  • An empty list means no connected store is available, and sections in degraded_parts are unavailable only this time — note them and continue rather than retrying. If a status is not AVAILABLE, inspect the returned status before choosing reauthorization; do not infer that every non-available state requires it.

  • Do not mix IDs: stores[].dsers_store_id for store-scoped tools, stores[].sales_channel_id for connection flows, supplier_apps[].supplier_platform_id for supplier scope, and supplier_apps[].accounts[].supplier_account_id for an exact supplier account. The account ID comes from upstream supplierId; it is not the account row id, user ID, email, or login name.

  • Only AliExpress and Alibaba.com support multiple supplier accounts. Pass supplier_account_id to place_orders_to_suppliers only when one of those platforms has multiple usable accounts and the user selected one; omit it for a single account and every other supplier platform.

  • Hidden stores are still returned — exclude or flag them when counting, and read each store in its own currency and timezone, not the account's.

  • For publish_products_to_stores, Shopify Shipping Profile choices come from stores[].shipping_profiles[].id and the chosen profile's locations[].id; fixed product-push choices remain in that Tool's input schema, while this Tool also returns dynamic languages and effective store defaults.

  • For a Shopify store, if stores[].shipping_profiles is empty, first call list_shopify_shipping_zones for the same store to obtain valid country codes and currency, then call create_shopify_shipping_profile. After creation succeeds, call list_stores again and use the refreshed stores[].shipping_profiles[].id and the selected profile's locations[].id; never invent or reuse stale IDs. [Side effects] Read-only; no store, authorization or push setting is changed. [Confirmation] None required; picking among matches is disambiguation.

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": "list_stores"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNoResponse detail level. full returns the complete response. account_context returns only stores and supplier apps/accounts, omitting pricing_currency, shipping_profiles, and push_configuration.full

Output Schema

NameRequiredDescriptionDefault
storesYesConnected sales stores owned by the authenticated account
supplier_appsYesVisible supplier-platform applications and their connected supplier accounts
degraded_partsNoSections unavailable during this read; other returned sections remain usable
push_configurationNoDynamic publish languages and effective per-store push defaults
toolcall_response_atYesUTC timestamp when the Tool response was returned, formatted as RFC3339.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: it states hidden stores are still returned, empty list means no connected store, degraded sections are transient, non-AVAILABLE statuses must be inspected rather than assumed to need reauthorization, and it spells out which ID field belongs to which downstream scope. The '[Side effects]' and '[Confirmation]' sections close the loop on mutation risk.

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?

Bracketed section headers (Store / What it does / When to use / When not to use / How to use / Side effects / Confirmation) make it scannable and front-loaded. It runs long for a single-parameter read tool, with several bullets that border on downstream workflow documentation, but almost every sentence carries actionable content.

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 read-only discovery tool with an output schema, the description supplies everything an agent needs: the response shape under each view, ID-selection rules per downstream tool, multi-account constraints for AliExpress/Alibaba, and the shipping-profile bootstrap sequence. Nothing material about calling 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% and the single `view` enum is fully documented in the schema, so the baseline is 3. The description adds genuine decision value by saying to omit `view` in most cases and to use `account_context` only when pricing, Shipping Profile, and push details are unneeded, plus restating the omitted fields.

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 concrete verb and resource: it 'lists connected seller stores' with named fields (application, country, currency, timezone, connection status) plus supplier applications and accounts. The '[When not to use]' block explicitly routes to search_store_products, get_pricing_rule, and start_store_reauthorization, so the agent can separate it from siblings without opening a schema.

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?

It gives explicit when-to-use conditions (user asks which stores are connected, about currency/timezone/status, or proactively before any store-scoped action), named alternatives for when-not-to-use, and trigger words. The 'How to use' block adds concrete decision rules: omit `view` by default, disambiguate on multiple matches, never write to all stores, and handle `degraded_parts` rather than retrying.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.