@proof-holdings/mcp-server

Official

Overview Schema Source Related Servers Discussions Admin

preview_template

Read-only

Preview a template with sample data before saving to see how the message appears with placeholder variables filled in for the chosen channel and message type.

Instructions

Preview a template with sample data before saving, as a sub-account would send it. Shows how the message will look with placeholder variables filled in.

ACCESS: needs a Proof account. Set PROOF_API_KEY and restart this server, then call this tool again. start_login does NOT open this tool.

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": {
      "channel": "<channel>",
      "message_type": "<message_type>",
      "body": "<body>"
    },
    "name": "preview_template"
  }
}

Input Schema

Name	Required	Description
`body`	Yes	Template body text
`channel`	Yes	Message channel
`subject`	No	Email subject line
`profile_id`	No	The sub-account to act on; omitted → your key's sub-account, or the primary sub-account for an account-wide key
`button_text`	No	Button text
`message_type`	Yes	Message type
`button_url_template`	No	Button URL template

Output Schema

Name	Required	Description
`preview`	No
`is_valid`	No
`warnings`	No	What a save would warn about; never makes `is_valid` false. Always sent; absent from an API that predates it.
`validation_errors`	No	What a save would refuse.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.7.2Nov 6, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / profile_id / description

Previous value: -"The sub-account (project) to act on; omitted → your key's project, or the primary project for an account-wide key"New value: +"The sub-account to act on; omitted → your key's sub-account, or the primary sub-account for an account-wide key"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "is_valid": {},
+    "preview": {},
+    "validation_errors": {
+      "description": "What a save would refuse."
+    },
+    "warnings": {
+      "description": "What a save would warn about; never makes `is_valid` false. Always sent; absent from an API that predates it."
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedv1.7.0Oct 16, 2026

addedInput schema / properties / profile_id

Added value: +{
+  "description": "The sub-account (project) to act on; omitted → your key's project, or the primary project for an account-wide key",
+  "pattern": "^[0-9a-fA-F]{24}$",
+  "type": "string"
+}

First observedv1.1.0Sep 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

The description is consistent with readOnlyHint=true — previewing implies no persistence. It goes meaningfully beyond the annotation by disclosing an authentication prerequisite (a Proof account plus PROOF_API_KEY set with a server restart) and by explicitly warning that start_login does Not satisfy that requirement, which would otherwise be a likely agent mistake.

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?

The core purpose and the timing condition come first in one tight sentence, followed by a rendering-behavior sentence and a separated access note. The access block is slightly verbose but is operationally necessary, and 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 an output schema present, return values need no explanation, and the definition covers purpose, timing, and the auth gate for a 7-parameter read-only tool. The one real gap is the unresolved overlap with render_template, which an agent cannot resolve from this text alone.

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 description coverage is 100% and two parameters carry enums, so the schema already carries the parameter burden; the baseline of 3 applies. The prose adds only marginal meaning — 'as a sub-account would send it' hints at profile_id semantics and 'placeholder variables' hints at button_url_template — without documenting any parameter directly.

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 states a specific verb and resource ('Preview a template with sample data') and clarifies the rendering semantics ('placeholder variables filled in', 'as a sub-account would send it'). It is immediately clear this is a non-persisting render preview, though it never distinguishes itself from the sibling render_template.

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?

'before saving' gives a concrete temporal context that selects this tool over the mutation siblings (update_template, create-style flows). However, no exclusion is stated, and the near-identical sibling render_template is never mentioned, leaving the agent to guess between the two.

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

Deploy Server