AIsa Agent Mail

Inboxes - Reply To Message

post_agentmail_inbox_message_reply

Destructive

Reply To Message

Published reference price: $0.012 USD per successful request. Account-specific pricing and final settlement may differ.

Input Schema

Name	Required	Description
`body`	No
`inbox_id`	Yes	The ID of the inbox.
`message_id`	Yes	ID of message.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedOct 19, 2026

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

removedInput schema / properties / attachments

Removed value: -{
-  "description": "Attachments to include in message.",
-  "items": {
-    "description": "Provide either `content` or `url` for each attachment.",
-    "properties": {
-      "content": {
-        "description": "Base64 encoded content of the attachment. The entire request, including the message body and all attachments, is limited to 6 MB.",
-        "type": "string"
-      },
-      "content_disposition": {
-        "description": "Content disposition of attachment.",
-        "enum": [
-          "inline",
-          "attachment"
-        ],
-        "title": "AttachmentContentDisposition",
-        "type": "string"
-      },
-      "content_id": {
-        "description": "Content ID of attachment.",
-        "title": "AttachmentContentId",
-        "type": "string"
-      },
-      "content_type": {
-        "description": "Content type of attachment.",
-        "title": "AttachmentContentType",
-        "type": "string"
-      },
-      "filename": {
-        "description": "Filename of attachment.",
-        "title": "AttachmentFilename",
-        "type": "string"
-      },
-      "url": {
-        "description": "URL that AgentMail can download without custom authentication headers or cookies.\nRedirects and pre-signed URLs are supported, and the final response must be a\nsuccessful 2xx response. Keep URL-backed attachments around 30 MB total per message.",
-        "type": "string"
-      }
-    },
-    "title": "SendAttachment",
-    "type": "object"
-  },
-  "title": "SendMessageAttachments",
-  "type": "array"
-}

removedInput schema / properties / bcc

Removed value: -{
-  "description": "BCC recipient address or addresses.",
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    }
-  ],
-  "title": "SendMessageBcc"
-}

addedInput schema / properties / body

Added value: +{
+  "properties": {
+    "attachments": {
+      "description": "Attachments to include in message.",
+      "items": {
+        "description": "Provide either `content` or `url` for each attachment.",
+        "properties": {
+          "content": {
+            "description": "Base64 encoded content of the attachment. The entire request, including the message body and all attachments, is limited to 6 MB.",
+            "type": "string"
+          },
+          "content_disposition": {
+            "description": "Content disposition of attachment.",
+            "enum": [
+              "inline",
+              "attachment"
+            ],
+            "title": "AttachmentContentDisposition",
+            "type": "string"
+          },
+          "content_id": {
+            "description": "Content ID of attachment.",
+            "title": "AttachmentContentId",
+            "type": "string"
+          },
+          "content_type": {
+            "description": "Content type of attachment.",
+            "title": "AttachmentContentType",
+            "type": "string"
+          },
+          "filename": {
+            "description": "Filename of attachment.",
+            "title": "AttachmentFilename",
+            "type": "string"
+          },
+          "url": {
+            "description": "URL that AgentMail can download without custom authentication headers or cookies.\nRedirects and pre-signed URLs are supported, and the final response must be a\nsuccessful 2xx response. Keep URL-backed attachments around 30 MB total per message.",
+            "type": "string"
+          }
+        },
+        "title": "SendAttachment",
+        "type": "object"
+      },
+      "title": "SendMessageAttachments",
+      "type": "array"
+    },
+    "bcc": {
+      "description": "BCC recipient address or addresses.",
+      "oneOf": [
+        {
+          "type": "string"
+        },
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        }
+      ],
+      "title": "SendMessageBcc"
+    },
+    "cc": {
+      "description": "CC recipient address or addresses.",
+      "oneOf": [
+        {
+          "type": "string"
+        },
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        }
+      ],
+      "title": "SendMessageCc"
+    },
+    "headers": {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "description": "Headers to include in message.",
+      "title": "SendMessageHeaders",
+      "type": "object"
+    },
+    "html": {
+      "description": "HTML body of message.",
+      "title": "MessageHtml",
+      "type": "string"
+    },
+    "labels": {
+      "description": "Labels of message.",
+      "items": {
+        "type": "string"
+      },
+      "title": "MessageLabels",
+      "type": "array"
+    },
+    "reply_all": {
+      "description": "Reply to all recipients of the original message.",
+      "title": "ReplyAll",
+      "type": "boolean"
+    },
+    "reply_to": {
+      "description": "Reply-to address or addresses.",
+      "oneOf": [
+        {
+          "type": "string"
+        },
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        }
+      ],
+      "title": "SendMessageReplyTo"
+    },
+    "text": {
+      "description": "Plain text body of message.",
+      "title": "MessageText",
+      "type": "string"
+    },
+    "to": {
+      "description": "Recipient address or addresses.",
+      "oneOf": [
+        {
+          "type": "string"
+        },
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        }
+      ],
+      "title": "SendMessageTo"
+    },
+    "track_opens": {
+      "description": "Track when this message is first opened. Requires a custom domain with tracking enabled and\nan HTML body. Opens surface as the `opened` label on the message and as a `message.opened`\nevent. One pixel is injected per message, not per recipient, so a message with several\nrecipients fires once when any of them opens it, and the event does not identify which one.",
+      "title": "TrackOpens",
+      "type": "boolean"
+    }
+  },
+  "title": "ReplyToMessageRequest",
+  "type": "object"
+}

removedInput schema / properties / cc

Removed value: -{
-  "description": "CC recipient address or addresses.",
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    }
-  ],
-  "title": "SendMessageCc"
-}

removedInput schema / properties / headers

Removed value: -{
-  "additionalProperties": {
-    "type": "string"
-  },
-  "description": "Headers to include in message.",
-  "title": "SendMessageHeaders",
-  "type": "object"
-}

removedInput schema / properties / html

Removed value: -{
-  "description": "HTML body of message.",
-  "title": "MessageHtml",
-  "type": "string"
-}

removedInput schema / properties / labels

Removed value: -{
-  "description": "Labels of message.",
-  "items": {
-    "type": "string"
-  },
-  "title": "MessageLabels",
-  "type": "array"
-}

removedInput schema / properties / reply_all

Removed value: -{
-  "description": "Reply to all recipients of the original message.",
-  "title": "ReplyAll",
-  "type": "boolean"
-}

removedInput schema / properties / reply_to

Removed value: -{
-  "description": "Reply-to address or addresses.",
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    }
-  ],
-  "title": "SendMessageReplyTo"
-}

removedInput schema / properties / text

Removed value: -{
-  "description": "Plain text body of message.",
-  "title": "MessageText",
-  "type": "string"
-}

removedInput schema / properties / to

Removed value: -{
-  "description": "Recipient address or addresses.",
-  "oneOf": [
-    {
-      "type": "string"
-    },
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    }
-  ],
-  "title": "SendMessageTo"
-}

removedInput schema / properties / track_opens

Removed value: -{
-  "description": "Track when this message is first opened. Requires a custom domain with tracking enabled and\nan HTML body. Opens surface as the `opened` label on the message and as a `message.opened`\nevent. One pixel is injected per message, not per recipient, so a message with several\nrecipients fires once when any of them opens it, and the event does not identify which one.",
-  "title": "TrackOpens",
-  "type": "boolean"
-}

Changed8 schema fields changedOct 16, 2026

removedInput schema / properties / bcc / anyOf

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

addedInput schema / properties / bcc / oneOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / cc / anyOf

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

addedInput schema / properties / cc / oneOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / reply_to / anyOf

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

addedInput schema / properties / reply_to / oneOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

removedInput schema / properties / to / anyOf

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

addedInput schema / properties / to / oneOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]

Changed6 schema fields changedOct 15, 2026

removedInput schema / properties / Authorization

Removed value: -{
-  "description": "Bearer authentication",
-  "type": "string"
-}

addedInput schema / properties / attachments / items / description

Added value: +"Provide either `content` or `url` for each attachment."

changedInput schema / properties / attachments / items / properties / content / description

Previous value: -"Base64 encoded content of attachment."New value: +"Base64 encoded content of the attachment. The entire request, including the message body and all attachments, is limited to 6 MB."

changedInput schema / properties / attachments / items / properties / url / description

Previous value: -"URL to the attachment."New value: +"URL that AgentMail can download without custom authentication headers or cookies.\nRedirects and pre-signed URLs are supported, and the final response must be a\nsuccessful 2xx response. Keep URL-backed attachments around 30 MB total per message."

addedInput schema / properties / track_opens

Added value: +{
+  "description": "Track when this message is first opened. Requires a custom domain with tracking enabled and\nan HTML body. Opens surface as the `opened` label on the message and as a `message.opened`\nevent. One pixel is injected per message, not per recipient, so a message with several\nrecipients fires once when any of them opens it, and the event does not identify which one.",
+  "title": "TrackOpens",
+  "type": "boolean"
+}

changedInput schema / required

Previous value: -[
-  "inbox_id",
-  "message_id",
-  "Authorization"
-]New value: +[
+  "inbox_id",
+  "message_id"
+]

Changed6 schema fields changedOct 15, 2026

addedInput schema / properties / Authorization

Added value: +{
+  "description": "Bearer authentication",
+  "type": "string"
+}

removedInput schema / properties / attachments / items / description

Removed value: -"Provide either `content` or `url` for each attachment."

changedInput schema / properties / attachments / items / properties / content / description

Previous value: -"Base64 encoded content of the attachment. The entire request, including the message body and all attachments, is limited to 6 MB."New value: +"Base64 encoded content of attachment."

changedInput schema / properties / attachments / items / properties / url / description

Previous value: -"URL that AgentMail can download without custom authentication headers or cookies.\nRedirects and pre-signed URLs are supported, and the final response must be a\nsuccessful 2xx response. Keep URL-backed attachments around 30 MB total per message."New value: +"URL to the attachment."

removedInput schema / properties / track_opens

Removed value: -{
-  "description": "Track when this message is first opened. Requires a custom domain with tracking enabled and\nan HTML body. Opens surface as the `opened` label on the message and as a `message.opened`\nevent. One pixel is injected per message, not per recipient, so a message with several\nrecipients fires once when any of them opens it, and the event does not identify which one.",
-  "title": "TrackOpens",
-  "type": "boolean"
-}

changedInput schema / required

Previous value: -[
-  "inbox_id",
-  "message_id"
-]New value: +[
+  "inbox_id",
+  "message_id",
+  "Authorization"
+]

Changed6 schema fields changedOct 15, 2026

removedInput schema / properties / Authorization

Removed value: -{
-  "description": "Bearer authentication",
-  "type": "string"
-}

addedInput schema / properties / attachments / items / description

Added value: +"Provide either `content` or `url` for each attachment."

changedInput schema / properties / attachments / items / properties / content / description

Previous value: -"Base64 encoded content of attachment."New value: +"Base64 encoded content of the attachment. The entire request, including the message body and all attachments, is limited to 6 MB."

changedInput schema / properties / attachments / items / properties / url / description

Previous value: -"URL to the attachment."New value: +"URL that AgentMail can download without custom authentication headers or cookies.\nRedirects and pre-signed URLs are supported, and the final response must be a\nsuccessful 2xx response. Keep URL-backed attachments around 30 MB total per message."

addedInput schema / properties / track_opens

Added value: +{
+  "description": "Track when this message is first opened. Requires a custom domain with tracking enabled and\nan HTML body. Opens surface as the `opened` label on the message and as a `message.opened`\nevent. One pixel is injected per message, not per recipient, so a message with several\nrecipients fires once when any of them opens it, and the event does not identify which one.",
+  "title": "TrackOpens",
+  "type": "boolean"
+}

changedInput schema / required

Previous value: -[
-  "inbox_id",
-  "message_id",
-  "Authorization"
-]New value: +[
+  "inbox_id",
+  "message_id"
+]

First observedSep 15, 2026

TDQS

D1.7/5.0

Behavior2/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered by structured data. The only behavioral content the description adds is a published price of $0.012 per successful request, which is marginally useful, but it says nothing about what the call actually does on the wire (new outbound message, thread linkage, irreversibility of sending).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short, but it is not concise so much as under-specified: the only substantive content is a pricing boilerplate block appended after a title restatement. Nothing is front-loaded that helps an agent act, so brevity here is a deficiency rather than an efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex mutation tool with a nested request body, three parameters, and message-thread semantics, and the description supplies none of the context an agent needs. The existence of an output schema and safety annotations does not compensate for the missing explanation of reply construction and sending behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67%, below the 80% threshold at which the schema alone justifies a 3. The description explains none of the three top-level parameters and does not clarify the reply-specific semantics of message_id or the nested body options (reply_all, to/cc/bcc, attachments size limits) that the schema only partially documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is literally the title restated ('Reply To Message'), which is the definition of a tautology under the rubric. It does imply replying to a message, but it offers no verb nuance, scope, or anything that separates it from post_agentmail_inbox_message_reply_all, post_agentmail_inbox_message_forward, or post_agentmail_inbox_message_send.

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

Usage Guidelines1/5

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

There is no usage guidance whatsoever. It never says when to reply versus reply-all versus forward, nor whether the reply is threaded onto message_id, nor what prerequisites (e.g., inbound message) must hold. Nothing routes the agent to the correct sibling.

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

All AIsa Agent 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.

Resources

Need Help?