ErzyCall

update_outbound_assistant

Update an outbound assistant after showing the exact proposed changes and confirming. voice, model, and transcriber are replaced as whole objects — fetch the current config with get_outbound_assistant and send it back with your edits applied, or omit the object entirely to leave it untouched.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No
`model`	No
`voice`	No
`confirmed`	Yes	Must be true only after the user explicitly confirms this exact operation
`isDefault`	No
`assistantId`	Yes
`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.

Changed2 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 / voiceRuntime

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

First observedSep 9, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only declare a non-read-only, non-destructive write. The description adds crucial behavior beyond them: the confirmation gate and, most importantly, that voice/model/transcriber are replaced as whole objects and must be round-tripped from get_outbound_assistant — a real data-loss trap the annotations do not convey.

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 action and confirmation rule, then the replacement semantics. No filler; every clause carries operational weight.

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?

An output schema exists so return values need no explanation, and the description covers the high-risk replacement behavior and confirmation workflow for a 16-param nested tool. It could go further on the undocumented scalar/boolean fields, but is nearly complete for the risky parts.

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 13% across 16 params, so the description must carry the load. It does add real semantics for the three nested objects (whole-object replacement / omit-to-leave-untouched), but the many booleans and remaining fields are undocumented in both schema and description, leaving substantive gaps.

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+resource ('Update an outbound assistant') and distinguishes itself from siblings by naming get_outbound_assistant as the read counterpart it must be paired with. An agent can separate this from create/delete/get for assistants without opening schemas.

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?

Gives a clear prerequisite workflow: show the exact proposed changes and get confirmation before updating, and fetch current config via get_outbound_assistant before editing. It lacks explicit when-not-to-use exclusions (e.g., vs create_outbound_assistant), so it stops short of a 5.

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?