m365-mcp

Send Email

email_send

Send a new email or existing draft after user approval; requires confirm=true and cannot be undone. Never infer recipients.

Instructions

Send an email now: a new message (mode='new') or a draft you created earlier (mode='draft'). Requires confirm=true after the user approves the recipients and content. Cannot be undone. Never infer recipients.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cc`	No	Cc recipients.
`to`	No	Recipients (To).
`bcc`	No	Bcc recipients.
`body`	No	Message body.
`mode`	Yes	Send a new message or an existing draft.
`confirm`	Yes	Must be true to send this email; set only after the user approves.
`subject`	No	Subject line.
`draft_id`	No	mode='draft': draft ID from email_create_draft.
`account_id`	No	Account ID or email address. Omit when only one account is signed in.
`importance`	No	Message importance.
`attachments`	No	Local files to attach: at most 10, each at most 25 MB.
`body_format`	No	Format of the body text you supply.	text
`save_to_sent`	No	mode='new': keep a copy in Sent Items.

Output Schema

TableJSON Schema

Name	Required	Description
`mode`	Yes
`status`	Yes
`sent_at`	Yes
`summary`	Yes	One-line human summary. The tool's text content is this result serialized as JSON (summary included), so a client that ignores structuredContent still sees every field.
`draft_id`	Yes
`recipient_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed44 schema fields changedv1.0.0Sep 29, 2026

addedInput schema / $schema

Added value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / account_id / description

Added value: +"Account ID or email address. Omit when only one account is signed in."

addedInput schema / properties / account_id / maxLength
```
Added value: +320
```
addedInput schema / properties / account_id / minLength
```
Added value: +1
```

removedInput schema / properties / attachments / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / attachments / default
```
Removed value: -null
```

addedInput schema / properties / attachments / description

Added value: +"Local files to attach: at most 10, each at most 25 MB."

addedInput schema / properties / attachments / items

Added value: +{
+  "description": "Local file path inside the server's allowed folders. Hidden and secret files are refused.",
+  "maxLength": 4096,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / attachments / maxItems
```
Added value: +10
```
addedInput schema / properties / attachments / type
```
Added value: +"array"
```
addedInput schema / properties / attachments / uniqueItems
```
Added value: +true
```

addedInput schema / properties / bcc

Added value: +{
+  "description": "Bcc recipients.",
+  "items": {
+    "description": "Email address, e.g. jane@example.com.",
+    "format": "email",
+    "maxLength": 320,
+    "minLength": 3,
+    "type": "string"
+  },
+  "maxItems": 500,
+  "type": "array",
+  "uniqueItems": true
+}

addedInput schema / properties / body / description
```
Added value: +"Message body."
```
addedInput schema / properties / body / maxLength
```
Added value: +1000000
```

addedInput schema / properties / body_format

Added value: +{
+  "default": "text",
+  "description": "Format of the body text you supply.",
+  "enum": [
+    "text",
+    "html"
+  ],
+  "type": "string"
+}

removedInput schema / properties / cc / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / cc / default
```
Removed value: -null
```
addedInput schema / properties / cc / description
```
Added value: +"Cc recipients."
```

addedInput schema / properties / cc / items

Added value: +{
+  "description": "Email address, e.g. jane@example.com.",
+  "format": "email",
+  "maxLength": 320,
+  "minLength": 3,
+  "type": "string"
+}

addedInput schema / properties / cc / maxItems
```
Added value: +500
```
addedInput schema / properties / cc / type
```
Added value: +"array"
```
addedInput schema / properties / cc / uniqueItems
```
Added value: +true
```

addedInput schema / properties / confirm / description

Added value: +"Must be true to send this email; set only after the user approves."

addedInput schema / properties / draft_id

Added value: +{
+  "description": "mode='draft': draft ID from email_create_draft.",
+  "maxLength": 1024,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / importance

Added value: +{
+  "description": "Message importance.",
+  "enum": [
+    "low",
+    "normal",
+    "high"
+  ],
+  "type": "string"
+}

addedInput schema / properties / mode

Added value: +{
+  "description": "Send a new message or an existing draft.",
+  "enum": [
+    "new",
+    "draft"
+  ],
+  "type": "string"
+}

addedInput schema / properties / save_to_sent

Added value: +{
+  "default": true,
+  "description": "mode='new': keep a copy in Sent Items.",
+  "type": "boolean"
+}

addedInput schema / properties / subject / description
```
Added value: +"Subject line."
```
addedInput schema / properties / subject / maxLength
```
Added value: +998
```
addedInput schema / properties / subject / minLength
```
Added value: +1
```

removedInput schema / properties / to / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  }
-]

addedInput schema / properties / to / description
```
Added value: +"Recipients (To)."
```

addedInput schema / properties / to / items

Added value: +{
+  "description": "Email address, e.g. jane@example.com.",
+  "format": "email",
+  "maxLength": 320,
+  "minLength": 3,
+  "type": "string"
+}

addedInput schema / properties / to / maxItems
```
Added value: +500
```
addedInput schema / properties / to / minItems
```
Added value: +1
```
addedInput schema / properties / to / type
```
Added value: +"array"
```
addedInput schema / properties / to / uniqueItems
```
Added value: +true
```

changedInput schema / required

Previous value: -[
-  "account_id",
-  "to",
-  "subject",
-  "body"
-]New value: +[
+  "mode",
+  "confirm"
+]

addedOutput schema / $schema

Added value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / additionalProperties

Previous value: -{
-  "type": "string"
-}New value: +false

addedOutput schema / description
```
Added value: +"Send confirmation."
```

addedOutput schema / properties

Added value: +{
+  "draft_id": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "mode": {
+    "enum": [
+      "new",
+      "draft"
+    ]
+  },
+  "recipient_count": {
+    "minimum": 0,
+    "type": "integer"
+  },
+  "sent_at": {
+    "format": "date-time",
+    "type": "string"
+  },
+  "status": {
+    "const": "sent"
+  },
+  "summary": {
+    "description": "One-line human summary. The tool's text content is this result serialized as JSON (summary included), so a client that ignores structuredContent still sees every field.",
+    "type": "string"
+  }
+}

addedOutput schema / required

Added value: +[
+  "status",
+  "mode",
+  "draft_id",
+  "recipient_count",
+  "sent_at",
+  "summary"
+]

First observedv0.2.3Jun 10, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations declare the safety profile (readOnly=false, idempotent=false, openWorld=true), so the bar is lower, and the description still adds the critical non-annotation fact: 'Cannot be undone.' That, plus the confirmation gate, is meaningful behavioral context. It stops short of permission/account requirements or delivery failure behavior.

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?

Three short sentences, no filler, with the action and mode split front-loaded and the irreversible/confinement constraints placed after. Every sentence carries a distinct rule.

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?

An output schema exists, so return values need not be explained, and the schema itself carries parameter detail. The description covers the irreversibility, the confirmation precondition, and recipient strictness, which are the highest-risk facts for this tool; deeper detail (account scoping, attachment limits) lives in the schema.

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%, so the schema already documents all 13 parameters including mode, confirm, and draft_id. The description restates mode semantics and the confirm gate, adding only marginal framing ('a draft you created earlier') beyond what the schema says.

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?

States a specific verb (send) and resource (email) and immediately splits the behavior into the two supported modes, mode='new' vs mode='draft'. This distinguishes it from sibling email_create_draft (which only stages) and from email_reply/email_forward.

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?

Gives a hard precondition (confirm=true only after the user approves recipients and content) and an explicit prohibition ('Never infer recipients'), which is exactly the kind of when-to-use guidance an agent needs. It does not explicitly name the alternative tools (create_draft, reply, forward) for cases where sending is premature.

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