Fluxmail

create_draft

Create an email draft for any connected account. For replies, pass replyToMessageId to auto-fill recipients and subject.

Instructions

Create a draft. For a reply draft, pass replyToMessageId (recipients/subject are derived; replyAll for reply-all).

Input Schema

TableJSON Schema

Name	Required	Description
`cc`	No	Recipients, each "Name <a@x.com>" or "a@x.com"
`to`	No	Recipients, each "Name <a@x.com>" or "a@x.com"
`bcc`	No	Recipients, each "Name <a@x.com>" or "a@x.com"
`from`	No	Connected address or an available send-as address
`subject`	No	Defaults to "Re: ..." when replying
`bodyHtml`	No	HTML body
`bodyText`	No	Plain-text body. Line breaks appear in the sent email. Keep each prose paragraph on one continuous line and separate paragraphs with blank lines.
`replyAll`	No	With replyToMessageId: reply to all original recipients
`accountId`	No	Account to operate on. Optional when exactly one account is connected.
`attachments`	No
`replyToMessageId`	No	Message being replied to; threads correctly and computes recipients if "to" is omitted

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.11.1Oct 1, 2026
- removedOutput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```

Changed2 schema fields changedv0.11.0Sep 26, 2026

changedInput schema / properties / bodyText / description

Previous value: -"Plain-text body"New value: +"Plain-text body. Line breaks appear in the sent email. Keep each prose paragraph on one continuous line and separate paragraphs with blank lines."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "properties": {
+        "accountId": {
+          "type": "string"
+        },
+        "attachments": {
+          "items": {
+            "additionalProperties": true,
+            "properties": {
+              "filename": {
+                "type": "string"
+              },
+              "id": {
+                "type": "string"
+              },
+              "mimeType": {
+                "type": "string"
+              },
+              "sizeBytes": {
+                "type": "number"
+              }
+            },
+            "required": [
+              "id",
+              "filename",
+              "mimeType",
+              "sizeBytes"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "body": {
+          "additionalProperties": false,
+          "properties": {
+            "html": {
+              "type": "string"
+            },
+            "text": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "bodyTruncation": {
+          "additionalProperties": {
+            "additionalProperties": false,
+            "properties": {
+              "nextOffset": {
+                "type": "number"
+              },
+              "totalChars": {
+                "type": "number"
+              }
+            },
+            "required": [
+              "totalChars"
+            ],
+            "type": "object"
+          },
+          "type": "object"
+        },
+        "date": {
+          "type": "string"
+        },
+        "flags": {
+          "additionalProperties": true,
+          "properties": {
+            "draft": {
+              "type": "boolean"
+            },
+            "read": {
+              "type": "boolean"
+            },
+            "starred": {
+              "type": "boolean"
+            }
+          },
+          "required": [
+            "read",
+            "starred",
+            "draft"
+          ],
+          "type": "object"
+        },
+        "id": {
+          "type": "string"
+        },
+        "subject": {
+          "type": "string"
+        },
+        "threadId": {
+          "type": "string"
+        },
+        "to": {
+          "items": {
+            "additionalProperties": true,
+            "properties": {
+              "email": {
+                "type": "string"
+              },
+              "name": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "email"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "required": [
+        "id",
+        "threadId",
+        "accountId",
+        "to",
+        "subject",
+        "date",
+        "flags"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "data"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv0.9.0Sep 16, 2026

addedInput schema / properties / from

Added value: +{
+  "description": "Connected address or an available send-as address",
+  "format": "email",
+  "type": "string"
+}

First observedv0.1.0Jul 26, 2026

TDQS

B3.2/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden. It never states the key behavioral fact that creating a draft does not send the email, nor any account/permission requirements or what happens to derived recipients/subject. It discloses only the reply-derivation behavior, leaving important traits unstated for a write operation.

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?

Two tight sentences, with the general purpose front-loaded and the reply-specific caveat second. No filler, though it is terse enough to leave gaps rather than being fully self-contained.

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?

An output schema exists, so return values need not be explained. For an 11-parameter mutation tool with no annotations, however, the description is thin: it omits the draft-vs-send distinction and account requirements, leaving the agent to infer behavior from the schema 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 91%, so the schema already documents nearly all 11 parameters, establishing a baseline of 3. The description adds some value by explaining that recipients and subject are derived when replying, but doesn't extend meaning for the many other parameters (from, attachments, accountId, body variants).

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?

States a clear verb+resource ('Create a draft') and additionally distinguishes the reply-draft mode from a plain draft via replyToMessageId. It doesn't explicitly name sibling tools like update_draft, but the reply-mode framing separates it from the other draft operations well enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives guidance for the reply case (pass replyToMessageId, use replyAll for reply-all), which is genuinely useful conditional routing. However, it says nothing about when to use create_draft versus send_email or preview_send, nor any prerequisites for composing a new draft.

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