ErzyCall

create_outbound_assistant

Create an outbound assistant after explicit confirmation. Show the user the name, voice, and model you intend to use and get their approval first. Omit transcriber to accept the platform standard.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes
`model`	No	Required for VAPI. Not used by LiveKit, which executes dynamicAgentConfig.
`voice`	No	Required for VAPI. Not used by LiveKit, which executes dynamicAgentConfig.
`confirmed`	Yes	Must be true only after the user explicitly confirms this exact operation
`isDefault`	No
`description`	No
`transcriber`	No
`firstMessage`	No
`systemPrompt`	No
`voiceRuntime`	No
`idempotencyKey`	Yes	A unique identifier generated once for this intended write. Reuse exactly when retrying.
`dynamicAgentConfig`	No
`backchannelingEnabled`	No
`dialKeypadFunctionEnabled`	No
`backgroundDenoisingEnabled`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`success`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 18, 2026

addedInput schema / properties / dynamicAgentConfig

Added value: +{
+  "anyOf": [
+    {
+      "properties": {
+        "gptLive": {
+          "properties": {
+            "backendModel": {
+              "type": "string"
+            },
+            "instructions": {
+              "type": "string"
+            },
+            "voice": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "voice",
+            "instructions"
+          ],
+          "type": "object"
+        },
+        "llm": {
+          "properties": {
+            "model": {
+              "type": "string"
+            },
+            "temperature": {
+              "type": "number"
+            }
+          },
+          "required": [
+            "model"
+          ],
+          "type": "object"
+        },
+        "preemptiveGeneration": {
+          "type": "boolean"
+        },
+        "stt": {
+          "properties": {
+            "language": {
+              "type": "string"
+            },
+            "model": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "model",
+            "language"
+          ],
+          "type": "object"
+        },
+        "tts": {
+          "properties": {
+            "language": {
+              "type": "string"
+            },
+            "model": {
+              "type": "string"
+            },
+            "voice": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "model",
+            "voice"
+          ],
+          "type": "object"
+        },
+        "version": {
+          "const": 1,
+          "type": "number"
+        }
+      },
+      "required": [
+        "version",
+        "llm",
+        "stt",
+        "tts"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

addedInput schema / properties / model / description

Added value: +"Required for VAPI. Not used by LiveKit, which executes dynamicAgentConfig."

addedInput schema / properties / voice / description

Added value: +"Required for VAPI. Not used by LiveKit, which executes dynamicAgentConfig."

addedInput schema / properties / voiceRuntime

Added value: +{
+  "enum": [
+    "vapi",
+    "livekit"
+  ],
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "name",
-  "voice",
-  "model",
-  "confirmed",
-  "idempotencyKey"
-]New value: +[
+  "name",
+  "confirmed",
+  "idempotencyKey"
+]

First observedSep 9, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations establish this is a non-read-only, non-destructive, closed-world write. The description adds meaningful behavior beyond that: it requires a user-confirmation gate before execution and names the exact fields the user must approve. It does not, however, explain idempotency handling or the side effects of creating the assistant.

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?

Three sentences, front-loaded with the action verb, with no filler. 'after explicit confirmation' and 'get their approval first' overlap slightly, a minor redundancy, but overall the text is tightly scoped.

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

Completeness3/5

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 no explanation, and the confirmation workflow is covered. But for a 15-parameter tool with nested objects and a vapi/livekit runtime split (model/voice for VAPI versus dynamicAgentConfig for LiveKit), the description leaves the agent without guidance on how those branches relate — a notable gap against this tool's complexity.

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 coverage is only 27% across 15 params, so the description must compensate. It partially does, calling out name, voice, and model, and adding real value with 'Omit transcriber to accept the platform standard' (clarifying the transcriber default). But the bulk of the parameters — dynamicAgentConfig, voiceRuntime, systemPrompt, firstMessage, idempotencyKey — get no semantic help.

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?

States a specific verb and resource ('Create an outbound assistant'), which is unambiguous and clearly distinct from the get/update/delete/list siblings in the outbound-assistant family. It does not, however, explicitly differentiate itself from adjacent creation tools (create_call, create_contact, create_case) that appear in the same sibling list.

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

Usage Guidelines3/5

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

The description imposes a clear procedural precondition ('after explicit confirmation... show the user the name, voice, and model... and get their approval first'), which is genuine usage guidance. However, it never states when to reach for this tool versus related creation tools, so routing guidance is only implied.

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

All ErzyCall 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?