Replai

Read conversation state

inbox_read

Read-onlyIdempotent

Reads conversation state and server's email reply context/digest, never routing input.

Input Schema

Name	Required	Description	Default
`agent_id`	Yes	Agent ID from agents_list or agent_create.
`conversation_id`	Yes	Conversation ID from inbox_list or conversations_search.

Output Schema

Name	Required	Default
`id`	Yes
`mode`	No	auto_reply
`status`	Yes
`contact`	No
`agent_id`	Yes
`group_id`	No
`can_reply`	No
`contact_id`	No
`group_name`	No
`started_at`	Yes
`waiting_on`	No
`inbox_views`	No
`is_resolved`	No
`reply_owner`	No	ai
`resolved_at`	No
`resolved_by`	No
`channel_type`	No
`email_health`	No
`last_message`	No
`member_count`	No
`email_subject`	No
`message_count`	No
`waiting_since`	No
`last_message_at`	No
`pending_actions`	No
`conversation_type`	No	direct
`group_picture_url`	No
`email_reply_target`	No
`last_message_preview`	No
`channel_connection_id`	Yes
`last_message_direction`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 4, 2026

addedOutput schema / $defs / MessagePreview

Added value: +{
+  "properties": {
+    "content": {
+      "$ref": "#/$defs/MessagePreviewContent"
+    },
+    "message_type": {
+      "title": "Message Type",
+      "type": "string"
+    }
+  },
+  "required": [
+    "message_type",
+    "content"
+  ],
+  "title": "MessagePreview",
+  "type": "object"
+}

addedOutput schema / $defs / MessagePreviewContent

Added value: +{
+  "description": "Language-neutral display facts, never vendor payloads or media credentials.",
+  "properties": {
+    "address": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Address"
+    },
+    "event_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Event Type"
+    },
+    "media_type": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Media Type"
+    },
+    "quick_reply_label": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Quick Reply Label"
+    },
+    "text": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Text"
+    },
+    "title": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Title"
+    }
+  },
+  "title": "MessagePreviewContent",
+  "type": "object"
+}

addedOutput schema / properties / last_message

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/MessagePreview"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

Changed2 schema fields changedOct 30, 2026
- addedInput schema / properties / agent_id / description
```
Added value: +"Agent ID from agents_list or agent_create."
```
- addedInput schema / properties / conversation_id / description
```
Added value: +"Conversation ID from inbox_list or conversations_search."
```

Changed1 schema field changedOct 30, 2026

changedOutput schema / properties / inbox_views / items / enum

Previous value: -[
-  "attention",
-  "contact",
-  "resolved",
-  "all"
-]New value: +[
+  "attention",
+  "contact",
+  "no_reply",
+  "resolved",
+  "all"
+]

Changed5 schema fields changedOct 30, 2026

changedOutput schema / description

Previous value: -"Conversation with contact info and message preview for list display."New value: +"The Inbox row keyed by Agent; resolution fields describe only a current resolution."

addedOutput schema / properties / agent_id

Added value: +{
+  "format": "uuid",
+  "title": "Agent Id",
+  "type": "string"
+}

removedOutput schema / properties / workspace_id

Removed value: -{
-  "format": "uuid",
-  "title": "Workspace Id",
-  "type": "string"
-}

changedOutput schema / required

Previous value: -[
-  "id",
-  "workspace_id",
-  "channel_connection_id",
-  "status",
-  "started_at"
-]New value: +[
+  "id",
+  "channel_connection_id",
+  "status",
+  "started_at",
+  "agent_id"
+]

changedOutput schema / title

Previous value: -"ConversationSummary"New value: +"InboxConversation"

Changed5 schema fields changedOct 28, 2026

addedOutput schema / $defs / FollowUpBlockedAction

Added value: +{
+  "properties": {
+    "kind": {
+      "const": "follow_up_blocked",
+      "title": "Kind",
+      "type": "string"
+    }
+  },
+  "required": [
+    "kind"
+  ],
+  "title": "FollowUpBlockedAction",
+  "type": "object"
+}

addedOutput schema / $defs / ReleaseCheckAction

Added value: +{
+  "properties": {
+    "kind": {
+      "const": "release_check",
+      "title": "Kind",
+      "type": "string"
+    }
+  },
+  "required": [
+    "kind"
+  ],
+  "title": "ReleaseCheckAction",
+  "type": "object"
+}

addedOutput schema / properties / pending_actions / items / discriminator / mapping / follow_up_blocked
```
Added value: +"#/$defs/FollowUpBlockedAction"
```
addedOutput schema / properties / pending_actions / items / discriminator / mapping / release_check
```
Added value: +"#/$defs/ReleaseCheckAction"
```

changedOutput schema / properties / pending_actions / items / oneOf

Previous value: -[
-  {
-    "$ref": "#/$defs/DeliveryCheckAction"
-  },
-  {
-    "$ref": "#/$defs/ReplyReviewAction"
-  },
-  {
-    "$ref": "#/$defs/ReplyNeededAction"
-  },
-  {
-    "$ref": "#/$defs/IssueReviewAction"
-  }
-]New value: +[
+  {
+    "$ref": "#/$defs/DeliveryCheckAction"
+  },
+  {
+    "$ref": "#/$defs/ReplyReviewAction"
+  },
+  {
+    "$ref": "#/$defs/ReplyNeededAction"
+  },
+  {
+    "$ref": "#/$defs/IssueReviewAction"
+  },
+  {
+    "$ref": "#/$defs/ReleaseCheckAction"
+  },
+  {
+    "$ref": "#/$defs/FollowUpBlockedAction"
+  }
+]

First observedOct 28, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The annotations already establish read-only, idempotent, non-destructive, closed-world behavior. The description adds that reply context is server-held and rules out routing, but the latter largely reinforces the existing safety annotations and no further operational behavior is disclosed.

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?

The single front-loaded sentence is efficient and contains no filler. However, the 'context/digest' shorthand and trailing 'never routing input' clause are compressed and slightly awkward, reducing precision.

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 simple read with two documented identifiers, comprehensive safety annotations, and an output schema, the description provides enough core scope to support invocation. Its main remaining gaps are sibling-selection guidance and a clearer explanation of what conversation state and reply context/digest contain.

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?

Both required UUID parameters are fully described in the schema, including sibling tools that can supply their values. The description adds no parameter-specific meaning beyond that complete schema coverage, so the baseline score of 3 applies.

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?

The description uses a specific read verb and identifies both conversation state and server-side email reply context/digest as the resources returned. It does not explicitly distinguish the tool from inbox_list or inbox_messages, and 'context/digest' leaves the exact scope somewhat ambiguous.

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?

The resource scope provides a reasonable use context, while 'never routing input' supplies an explicit when-not condition. It still lacks comparisons with sibling read tools and does not name an alternative for routing, so it does not merit a 5.

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

All Replai 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?