Skip to main content
Glama
Sign In

Fudge for Shopify

by ai.fudge
OverviewDiscussionsAdmin

Message Fudge

message_fudge

Ask Fudge to do work for this store: build or revise a page, article or other draft, investigate, or answer a question. Without ref, starts a new conversation; with ref, continues that work. Uses the store’s Fudge credits. requestId makes retries deliver once. Publishing always needs the merchant’s own approval in Fudge.

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": {
      "message": "<message>",
      "requestId": "<requestId>"
    },
    "name": "message_fudge"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNofudge://thread/… or fudge://project/… to continue; omit to start new work.
storeNoThe connected store to use. Omit when only one is connected.
titleNoShort title for a new conversation.
messageYesThe merchant’s request in full: what to do, for which page or products, and any decisions already made.
deliveryNosteer
requestIdYesA unique ID you choose for this request, e.g. a UUID. Retries reuse it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare safety flags, so the description adds real value: it discloses that the store's Fudge credits are consumed, that `requestId` provides retry de-duplication, and that publishing requires the merchant's own approval. It does not say whether the call returns immediately or runs asynchronously, which matters for a work-delegation tool.

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, then the ref rule, then cost and safety facts — no filler. Slightly dense with back-to-back clauses, but every sentence carries distinct information.

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?

There is no output schema, so the description should explain what the agent receives back (a thread ref, status, or completion signal) and whether the work is synchronous; it omits both. For a broad delegation tool with six parameters, the missing return-shape guidance is a meaningful gap.

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 83%, so the baseline is 3. The description reinforces the `ref` semantics and the `requestId` retry contract, but the `delivery` enum ('steer' vs 'queue') has no description in the schema or the text, and `store`/`title` behavior is left entirely to the schema.

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 description gives a specific verb+resource ('Ask Fudge to do work for this store') and enumerates the work types (build/revise a draft, investigate, answer a question). It distinguishes itself from direct-edit siblings implicitly by framing itself as delegating work to Fudge, though it never names a specific alternative.

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?

The `ref` rule is stated explicitly: omit to start new work, include to continue a thread or project. Credit consumption and the approval gate for publishing give clear preconditions, but there is no explicit comparison to sibling tools like create_draft_page or edit_draft_content for agents deciding which path to take.

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

All Fudge for Shopify toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources