Skip to main content
Glama

Set up a store before it goes live

set_up_store
DestructiveIdempotent

Sets up a store that is not live yet, in one call: the shop's website (only that site may then show the chat; its www twin is added), the chat's colours and button position, the header title, greeting and starter questions in one language, the tone and wording, a welcome and a goodbye popup, the countries the shop sells to, and switches (add to cart, ratings, photos, suggested replies). Only the given fields change. A greeting that does not say, in its language, that shoppers are talking to an AI assistant is refused. Voice is switched on or off only on the dashboard. Order lookup is not set here: it needs the Order status rule, added and tested in Rules on the dashboard. Refused once the store's chat is live on the shop.

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": {
      "store_id": "<store_id>"
    },
    "name": "set_up_store"
  }
}

Input Schema

NameRequiredDescriptionDefault
toneNo
titleNo
photosNoShoppers can send a photo, e.g. of a product.
ratingsNoShoppers are asked to rate the chat after it.
websiteNoThe shop's address, e.g. 'https://myshop.com'.
greetingNoThe welcome message.
languageNoLanguage of title, greeting and starter questions, e.g. 'en'. One language per call.
positionNo
store_idYesThe store's store_id (not its name).
add_to_cartNo
primary_colorNoButtons and header, e.g. '#1e1b4b'.
goodbye_messageNoA short popup when a visitor is about to leave, in language. '' switches it off.
secondary_colorNo
welcome_messageNoA short popup new visitors see after a few seconds, in language. '' switches it off.
sell_to_countriesNoTwo-letter codes of the countries the shop sells to; the chat answers only visitors there. [] answers everyone. Not needed for a shop that sells worldwide.
starter_questionsNoQuestions shoppers can tap, in a shopper's own words. Replaces that language's list.
custom_instructionsNoWording preferences per situation. Wording only: facts and prices belong on the shop's pages.
follow_up_suggestionsNoSuggested replies under the chat's answers.

Output Schema

NameRequiredDescriptionDefault
noteNo
changedYes
installNo
try_urlNo
store_idYes
chat_settingsYes
allowed_domainsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true and openWorldHint=false. Beyond those, the description adds two concrete behaviors the annotations cannot carry: partial semantics ("Only the given fields change", consistent with the idempotent hint) and a validation gate ("A greeting that does not say ... that shoppers are talking to an AI assistant is refused"). That is genuine added context, though it never explains the interaction between destructiveHint=true and the partial-update claim, nor says what a refusal looks like to the caller.

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

Conciseness3/5

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

The lead clause is well front-loaded and the refusal rules are crisply stated, but the middle is a long comma-chained inventory of nearly every property, several of which the schema already describes. Those list items largely restate structured data and make the paragraph slower to scan than a short purpose statement followed by the two or three true constraints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that creates and then rejects, with 18 parameters, coverage is decent: output schema means return values need no explanation, and the live-check refusal, partial-update semantics, per-language greeting validation and out-of-scope items (voice, order lookup) are all disclosed. Two things an agent would want are absent: how store_id is obtained (create_store vs. list_stores) and whether the refusal is permanent for that store or only until it is un-launched.

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 coverage is 72%, so most parameters are already documented and the baseline sits near 3. The description does add grouping and intent (colours/button position, tone and wording, the switches) and restates the one-language-per-call rule for language-dependent fields, but it introduces no timestamp, format or interaction nuance beyond the schema's own descriptions.

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?

The definition opens with a specific verb and resource plus an explicit scope guard: "Sets up a store that is not live yet, in one call", then enumerates exactly what gets configured (website, colours, greeting, popups, countries, switches). It is unmistakably a pre-launch setup tool. It never names a sibling such as apply_store_settings or propose_store_settings, so the reader has to infer the pre-launch vs. live distinction from the description alone.

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?

It clearly states the usable window with "Refused once the store's chat is live on the shop", and routes two adjacent capabilities elsewhere: voice changes go to the dashboard, order lookup requires the Order status rule in Rules. Those are real when/what-instead pointers. It stops short of naming the in-catalog alternatives an agent would need for choosing between this and the other settings tools.

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.

Resources