clover-mcp

draft_customer_message

Read-only

Draft customer messages for promo, win-back, or thank-you intents from a customer ID. Get a ready-to-review draft without sending anything.

Instructions

AI: draft a customer message (promo / win-back / thank-you) for the given intent.

Returns a DRAFT only — never sends anything. Needs a sampling-capable client (graceful fallback otherwise). Requires CUSTOMERS_R.

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": {
      "customer_id": "<customer_id>",
      "intent": "<intent>"
    },
    "name": "draft_customer_message"
  }
}

Input Schema

Name	Required	Description	Default
`intent`	Yes
`customer_id`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.7.0Aug 7, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description explicitly explains key behaviors: it never sends anything, requires a sampling-capable client with graceful fallback, and needs the CUSTOMERS_R permission. This adds substantial context that annotations alone do not convey, including permission and runtime requirements.

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

Conciseness5/5

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

The description is only three sentences, front-loaded with the primary action, followed by essential caveats. Every sentence adds value with no repetition or fluff, making it highly concise and well-structured.

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?

Given the simple two-parameter schema and existing output schema, the description covers all major aspects: purpose, side-effect safety, technical requirements, and permissions. It is complete enough for an agent to correctly select and invoke the tool.

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?

The input schema provides only names and types with zero descriptions. The description partially compensates by explaining that 'intent' refers to the type of message (promo/win-back/thank-you), but it does not explicitly clarify 'customer_id' or confirm the allowed values for intent. Since schema coverage is 0%, the description should do more, but it does add some meaning.

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 clearly states the tool's function with a specific verb ('draft') and resource ('customer message'), and lists the intents (promo, win-back, thank-you). It is unambiguous and distinguishes itself from all sibling tools, none of which deal with message drafting.

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 description clearly indicates when to use the tool: when a draft for a specific customer intent is needed. It also clarifies that it only returns a draft and never sends, setting expectations. However, it does not explicitly mention alternative tools or exclusions, though no alternative exists among siblings.

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

Deploy Server