Meridian

List CRM Custom Fields

custom_fields_list

Read-only

Lists an app's CRM custom field definitions: custom_field_id, handle (the key a value write is addressed to), name, type (text, number, boolean, select, date, or json), options (the allowed values of a select field), segment_operators (the operators a segment condition on this field may use; empty for json, which is not filterable), readable_by_app (whether GET /public/me returns the value to the app, where the merchant's browser can see it; set in the dashboard, off by default for a new field), and values_count (how many stores currently have a value). Takes the app_id returned by apps_list.

Pass shop_domain to additionally resolve that store's value for every definition, returned under values as a handle => value map. Fields the store has no value for are omitted from that map. Definitions require crm.custom_fields.view; resolving a store's values also requires crm.merchants.view.

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": {
      "app_id": "<app_id>"
    },
    "name": "custom_fields_list"
  }
}

Input Schema

Name	Required	Description
`app_id`	Yes	The app uuid returned by `apps_list`.
`shop_domain`	No	Optional myshopify domain (e.g. "acme.myshopify.com"). When supplied, that store's current value for each definition is returned as well.
`organization_id`	No	An organisation uuid or slug. When supplied, `app_id` is resolved within that organisation and may be a slug instead of a uuid, mirroring the Meridian web app.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare a safe read-only, closed-world operation, and the description adds substantive context beyond them: required permissions per mode, that `readable_by_app` is dashboard-set and off by default for new fields, that `json` fields are not filterable, and that stores lacking a value are omitted from the `values` map. These are behavioral details an agent could not infer from the annotations.

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?

Purpose is front-loaded in the first clause, and the long parenthetical field-by-field breakdown is justified because there is no output schema. Some density could be trimmed (the `readable_by_app` explanation is verbose), but no sentence is pure filler.

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

Completeness4/5

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

With no output schema, the description properly takes on the burden of describing the returned shape, and it covers permissions, both modes, and value-map semantics. Gaps remain: `organization_id` is undocumented, and nothing is said about result size or pagination.

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 would be 3; the description earns more by explaining the consequence of `shop_domain` (per-handle value map, missing entries omitted) and by tying `app_id` to `apps_list`. `organization_id` is never mentioned in the description, leaving it entirely to the schema.

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 first sentence gives a specific verb and resource ("Lists an app's CRM custom field definitions") and then enumerates exactly which fields come back, including the six allowed `type` values. It is clearly distinguishable from siblings like `custom_field_values_set` (writes values) and `apps_list` (source of `app_id`).

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 gives a clear conditional: pass `shop_domain` to additionally resolve per-store values, and omit it to get definitions only. It also names the prerequisite permissions (`crm.custom_fields.view`, plus `crm.merchants.view` for value resolution) and points to `apps_list` as the source of `app_id`. It stops short of naming an alternative tool or stating when not to use this one.

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

All Meridian tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?