Skip to main content
Glama
Cresca MCP Server

Cresca MCP Server

Create template

create_template

Create a draft email template with HTML, subject, and {{{VARIABLE}}} placeholders; publish it later before sending.

Instructions

POST /templates. Creates a template DRAFT (it cannot be sent until publish_template is called). Use {{{VARIABLE}}} placeholders in html, text, subject and preview_text. The template also appears under Transactional > Templates in the Cresca app. Needs a full-access key. Returns { object: "template", id }.

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": {
      "name": "<name>",
      "html": "<html>"
    },
    "name": "create_template"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNoDefault sender, e.g. "Acme <hello@acme.com>".
htmlYesHTML body. Use {{{VARIABLE}}} placeholders for values sent by the app.
nameYesTemplate name, up to 120 characters, unique in the account.
textNoPlain-text version. If omitted, it is generated from the HTML at send time.
aliasNoReadable id for sending, e.g. "password-reset": lowercase letters, numbers, dashes and underscores, up to 64 characters, unique in the account.
subjectNoDefault subject. Can contain variables.
reply_toNoDefault Reply-To address.
variablesNoUp to 50 variable definitions. Undeclared placeholders are added as string variables without a fallback on publish.
preview_textNoInbox preview snippet shown after the subject, up to 500 characters. Can contain variables.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, non-destructive, open-world. The description adds context annotations cannot carry: the result is a draft not a live template, and it "Needs a full-access key" — a real auth prerequisite an agent must satisfy before calling. It also discloses the return shape `{ object: "template", id }`, which matters since there is no output schema.

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?

Four short sentences, front-loaded with the operation and the draft constraint before the incidental UI note. The Cresca app navigation sentence is the weakest line and could be dropped, but nothing else is padding.

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?

For a 9-parameter create tool with no output schema, the definition covers the essentials: draft semantics, auth requirement, placeholder convention, and return payload. It does not mention uniqueness/conflict failure modes for name and alias, which is the main remaining gap for an agent anticipating errors.

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 100%, so the baseline is 3. The description does add the cross-cutting placeholder convention (`{{{VARIABLE}}}`) and extends it to text and preview_text, which the per-field schema descriptions only mention for html and subject — a modest but genuine addition beyond 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?

"POST /templates. Creates a template DRAFT" gives a specific verb and resource, and immediately scopes the result as a draft that is not sendable, which cleanly separates it from publish_template. An agent can tell exactly what this tool produces 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?

Explicitly states the lifecycle follow-up: the draft "cannot be sent until publish_template is called," naming the sibling that completes the flow. It does not say when to prefer update_template over creating a new one, nor what to do if the name/alias already exists, so it stops short of full when/when-not guidance.

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