Chatway Live Chat

Assign Conversation

assign-conversation

Assign or unassign an agent on one or more Chatway conversations. Identify the agent by UUID or an unambiguous name/email query, send all conversation UUIDs in one call, and obtain user confirmation before changing assignments. Use list-agents only when an agent_query match is ambiguous.

Input Schema

TableJSON Schema

Name	Required	Description
`agent_id`	No	Agent UUID to assign or unassign. Required unless agent_query is provided.
`agent_query`	No	Agent name or email to resolve (e.g. "Nibir"). Required unless agent_id is provided. Use list-agents if the match is ambiguous.
`conversation_ids`	Yes	Conversation UUIDs to assign, from 1 to 100.
`confirmation_token`	No	Required after the confirmation challenge. Ask the user to approve before calling again with this token.

Output Schema

TableJSON Schema

Name	Required	Description
`agent`	No
`queued`	No	True when several conversations were queued as background jobs.
`message`	No	Message describing the action or its result.
`agent_id`	No	UUID of the assigned agent.
`ambiguous`	No	True when agent_query matched several agents; pick one from candidates.
`candidates`	No	Agents matching an ambiguous agent_query.
`affected_count`	No	Number of records the action will change.
`confirmation_token`	No	Pass back as confirmation_token after the user approves.
`expires_in_seconds`	No	How long the confirmation token stays valid.
`confirmation_required`	No	True when the user must approve before the action runs.
`queued_conversation_ids`	No	Conversation UUIDs queued for the action.
`skipped_conversation_ids`	No	Conversation UUIDs that were skipped.
`assigned_conversation_ids`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 15, 2026

changedInput schema / properties / conversation_ids / description

Previous value: -"Conversation UUIDs to assign."New value: +"Conversation UUIDs to assign, from 1 to 100."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "affected_count": {
+      "description": "Number of records the action will change.",
+      "type": "integer"
+    },
+    "agent": {
+      "properties": {
+        "email": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "id": {
+          "description": "Agent UUID.",
+          "type": "string"
+        },
+        "name": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "type": "object"
+    },
+    "agent_id": {
+      "description": "UUID of the assigned agent.",
+      "type": "string"
+    },
+    "ambiguous": {
+      "description": "True when agent_query matched several agents; pick one from candidates.",
+      "type": "boolean"
+    },
+    "assigned_conversation_ids": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "candidates": {
+      "description": "Agents matching an ambiguous agent_query.",
+      "items": {
+        "properties": {
+          "email": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "id": {
+            "description": "Agent UUID.",
+            "type": "string"
+          },
+          "name": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "confirmation_required": {
+      "description": "True when the user must approve before the action runs.",
+      "type": "boolean"
+    },
+    "confirmation_token": {
+      "description": "Pass back as confirmation_token after the user approves.",
+      "type": "string"
+    },
+    "expires_in_seconds": {
+      "description": "How long the confirmation token stays valid.",
+      "type": "integer"
+    },
+    "message": {
+      "description": "Message describing the action or its result.",
+      "type": "string"
+    },
+    "queued": {
+      "description": "True when several conversations were queued as background jobs.",
+      "type": "boolean"
+    },
+    "queued_conversation_ids": {
+      "description": "Conversation UUIDs queued for the action.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "skipped_conversation_ids": {
+      "description": "Conversation UUIDs that were skipped.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

First observedOct 15, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only say the tool is not read-only and not destructive; the description goes further by disclosing the two-step confirmation requirement and the confirmation_token flow, which materially shapes how an agent must call it. It also bounds the batch size, though it does not say whether unassigning clears other agent state or what the confirmation challenge consists of.

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?

Two sentences, front-loaded with the mutation scope and followed by the workflow constraints. Every clause carries actionable content and nothing is padding.

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 values need no explanation, and annotations plus the 100% schema coverage carry the structural detail. The description adds the confirmation workflow and batch constraint; the only real gap is not steering the agent away from the overlapping handoff-to-human sibling.

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 agent_id vs agent_query mutual exclusivity, the 1-100 conversation_ids range, and the confirmation_token. The description mostly restates those facts (UUID or name/email lookup, all UUIDs in one call) rather than adding new meaning, so baseline 3 applies.

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?

The description opens with a specific verb pair ('assign or unassign') applied to a precise resource ('an agent on one or more Chatway conversations'), so the operation and its scope are unambiguous. It implicitly separates itself from siblings like get-conversation or list-conversations by being a mutation on assignments, and it names list-agents as the resolution fallback.

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?

It gives clear operational guidance: batch all conversation UUIDs into one call, get user confirmation before changing assignments, and use list-agents only when an agent_query match is ambiguous. That condition for the alternative is explicit, but there is no guidance distinguishing this from the conceptually adjacent sibling handoff-to-human, which an agent could easily confuse with assignment.

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

All Chatway Live Chat 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?