ErzyCall

update_inbound_assistant

Update an inbound voice assistant after reading it and explicitly confirming the exact change. Pass the opaque revision from get_inbound_assistant with either systemPrompt text or systemPromptId selection. Text creates an assistant-local prompt without mutating a shared library prompt. For transient assistants it applies to new calls. For permanent assistants it is allowed only when WhatsApp routes on active integrations are listed, applies only to new WhatsApp LiveKit calls, and leaves the provider-hosted phone prompt unchanged; archived integrations do not qualify, while a disabled call config remains visible with enabled=false. Permanent assistants without qualifying WhatsApp routes return UNSUPPORTED_CONFIG_MODE. systemPrompt and systemPromptId are mutually exclusive. Use update_whatsapp_agent for TEXT CHAT prompts.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No
`confirmed`	Yes	Must be true only after the user explicitly confirms this exact operation
`assistantId`	Yes
`systemPrompt`	No
`idempotencyKey`	Yes	A unique identifier generated once for this intended write. Reuse exactly when retrying.
`systemPromptId`	No
`expectedRevision`	No	Opaque revision from get_inbound_assistant; echo it unchanged

Output Schema

TableJSON Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 3, 2026

addedInput schema / properties / expectedRevision

Added value: +{
+  "description": "Opaque revision from get_inbound_assistant; echo it unchanged",
+  "maxLength": 300,
+  "pattern": "^ia1_[A-Za-z0-9_-]+$",
+  "type": "string"
+}

addedInput schema / properties / systemPrompt

Added value: +{
+  "maxLength": 50000,
+  "minLength": 1,
+  "type": "string"
+}

First observedSep 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations (readOnly=false, destructive=false, openWorld=false), the description discloses substantial behavior: text creates an assistant-local prompt without mutating a shared library prompt, permanent-assistant gating on active WhatsApp integration routes, that the provider-hosted phone prompt is left unchanged, archived vs disabled integration handling, and the UNSUPPORTED_CONFIG_MODE error. This is rich, non-redundant behavioral context.

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 purpose and precondition are front-loaded, and every sentence carries information. However, it is a dense run-on of semicolon-separated clauses, which could be grouped more readably for an agent parsing edge cases.

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

Completeness5/5

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

For a mutation tool with an output schema already present, the description covers preconditions, failure modes, mutual exclusivity, and side effects on shared vs local prompts. An agent has everything needed to invoke it correctly.

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

Parameters4/5

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

Schema coverage is only 43%, but the description compensates meaningfully, explaining systemPrompt vs systemPromptId semantics and their mutual exclusivity and reinforcing the revision/confirmation flow. It does not clarify `name` or `assistantId`, so it stops short of full coverage.

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?

It gives a specific verb and resource ('Update an inbound voice assistant') and explicitly scopes it as voice rather than text chat by pointing to update_whatsapp_agent for TEXT CHAT prompts. An agent can distinguish it from update_outbound_assistant and the outbound siblings without opening a schema.

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

Usage Guidelines5/5

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

It states the precondition (read via get_inbound_assistant and explicitly confirm the exact change), the required input flow (pass the opaque revision plus either systemPrompt or systemPromptId), and explicitly names the alternative tool for the text-chat case. Conditions for transient vs permanent assistants are spelled out.

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?