Skip to main content
Glama

Propose a settings change

propose_store_settings
Read-onlyIdempotent

Validates a proposed change to one store's settings, live or not, with the dashboard's own checks, and returns each setting before and after with a change_token valid for 15 minutes. Saves nothing. Covered: header title, greeting and starter questions and the welcome and goodbye popups, in one language the chat already speaks per call; colours; handoff on or off, business hours, time zone and the away and in-hours messages (one text for every language); switches (add to cart, ratings, photos, suggested replies); promoted products; switching rules off. Changed only on the dashboard: voice, custom instructions and tone, the pages, the allowed websites, the country filter, the monthly cap, going live, sign-in methods, the team, and connecting channels or a mailbox. Needs the settings permission and works only for stores the person owns.

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>",
      "changes": "<changes>"
    },
    "name": "propose_store_settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
changesYes
store_idYesThe store's store_id (not its name).

Output Schema

NameRequiredDescriptionDefault
savedYes
changesYes
store_idYes
change_tokenYes
expires_in_minutesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description adds material context beyond them: validation uses the dashboard's own checks, nothing is persisted, the returned change_token expires in 15 minutes, and each setting is returned before and after. It also discloses auth ('needs the settings permission') and ownership limits, which annotations cannot express.

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 the core action, non-persistence, and token lifetime before the supporting enumeration, so an agent gets the essentials in the first sentence. The covered/excluded catalogues are dense run-on lists that lean slightly toward completeness over economy, but each item earns its place by scoping the large nested schema.

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 two-parameter tool wrapping a large nested object, the definition covers purpose, validation semantics, token lifetime, permissions, ownership, and in-scope versus out-of-scope fields. An output schema exists, and the description still usefully previews the before/after shape and change_token, so nothing an agent needs 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?

With schema description coverage at 50% and a deeply nested changes object, the description compensates well: it constrains language to 'one the chat already speaks per call', clarifies that away/in-hours messages are 'one text for every language', and explains rules_off as switching off live rules. It does not touch every nested key (photos, ratings, follow_up_suggestions are only implied by the 'switches' list), leaving some gaps the schema must fill.

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 specific verb and resource (validate a proposed change to one store's settings) and pins the scope precisely: live or not, with the dashboard's own checks, returning before/after per setting plus a change_token. The explicit 'Saves nothing' plus the enumerated covered/uncovered settings let an agent separate this from a committing sibling like apply_store_settings without opening the schema.

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?

Strong context: it states the validation-only nature, the permission required ('settings permission'), and the ownership precondition ('works only for stores the person owns'), and enumerates which settings are in scope versus dashboard-only. It never names the apply tool explicitly, so the follow-up commit step must be inferred from 'Saves nothing' rather than being routed to directly.

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