Multi Mail

Send a message

messages_send

DestructiveIdempotent

Compose a new message in a connected mailbox and send it in one call. Call this only when the person asked for this message to go; when they asked to prepare one, draft it instead. A request id already spent sends nothing again: the answer says whether that send went or may have gone.

Input Schema

TableJSON Schema

Name	Required	Description
`cc`	No	Who to copy.
`to`	Yes	Who the message is addressed to.
`bcc`	No	Who to blind-copy. The other recipients are not told.
`body`	Yes	The message text.
`html`	No	The message as HTML, for formatting; body stays its plain-text version. An Outlook mailbox keeps only the HTML and writes the plain version from it.
`mailbox`	Yes	The mailbox's name or its email address.
`subject`	Yes	The subject line.
`requestId`	Yes	Your own id for this send, new for every message. One whose send went or may have gone sends nothing again.
`attachments`	No	Files to carry: one held by a connected mailbox of the message's own provider, or content you write out.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes
`accepted`	No
`threadId`	Yes
`messageId`	No
`sentCopyKept`	No
`refusedRecipients`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 8, 2026
- addedOutput schema / properties / sentCopyKept
```
Added value: +{
+  "const": false,
+  "type": "boolean"
+}
```

Changed2 schema fields changedOct 8, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed1 schema field changedOct 8, 2026
- addedOutput schema / properties / refusedRecipients
```
Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
```

Changed7 schema fields changedOct 6, 2026

changedInput schema / properties / bcc / items / pattern

Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"

changedInput schema / properties / cc / items / pattern

Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"

changedInput schema / properties / to / items / pattern

Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"

removedOutput schema / properties / id / anyOf

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

addedOutput schema / properties / id / type

Added value: +[
+  "string",
+  "null"
+]

removedOutput schema / properties / threadId / anyOf

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

addedOutput schema / properties / threadId / type
```
Added value: +[
+  "string",
+  "null"
+]
```

First observedOct 5, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare destructive=true, idempotent=true and openWorld=true. The description goes beyond them by explaining the practical meaning of the idempotency key — a spent request id resends nothing and the response reports whether the send went or may have gone — which is genuinely useful retry guidance not encoded in the hints.

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 sentences, each doing distinct work: what it does, when to use it, and the idempotency contract. Front-loaded and free of 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 shape need not be described, and the description covers the actionable decision plus retry semantics. Minor gap: it doesn't mention authentication/send-as identity or attachment-provider constraints, though those are largely captured in schema descriptions.

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 every parameter including requestId, html, and attachments is already documented in the schema. The description reinforces the requestId contract but adds no format or syntax detail beyond it; baseline 3 is appropriate.

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 and resource (compose and send a message in a connected mailbox) and explicitly separates itself from the drafting path. An agent can tell it apart from drafts_create / drafts_send without opening a 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 gives the selection rule: call only when the person asked the message to go, otherwise draft. It does not name the sibling tools (drafts_create, drafts_send) or address reply/forward variants, but the when/when-not condition is unambiguous.

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

All Multi Mail tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.