CallMCP — Phone Call MCP Server

Request Agent Change With Approval

request_agent_update

DestructiveIdempotent

Change a live agent's name, greeting, prompts, voice, model, call length or call transfer through the approval-gated path, for changes made on the owner's behalf that need a recorded approval. Needs agent_id, at least one field to change and the owner's confirmed approval. Callers hear the change on their next call. Direct edits by the owner go through update_agent_config. Returns needs_user_input, needs_approval, pending_approval, executed, denied or unsupported; only executed means the change was made.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent_id": "<agent_id>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "request_agent_update"
  }
}

Input Schema

Name	Required	Description
`name`	No	The name the agent uses.
`actor`	No	Do not set. Kept for older clients; the signed-in connection identifies you.
`model`	No	Language model settings: { provider, model }.
`voice`	No	Voice to use, from list_voices: { provider, voiceId }.
`reason`	No	Why the change is being made; kept in the audit log.
`dry_run`	No	Check access, inputs and approval without making the change.
`sms_llm`	No	Model for text replies.
`agent_id`	Yes	The agent to change.
`metadata`	No	Agent metadata to merge.
`authority`	No	Do not set. It cannot approve a change: the owner approves through review_url or by being signed in.
`sms_prompt`	No	Instructions for text replies.
`source_ref`	No	Optional reference for the request, such as a ticket or automation run ID.
`business_id`	No	Business ID. Required when the token can reach more than one business.
`max_duration`	No	Longest call length, in seconds.
`outbound_llm`	No	Model for outgoing calls.
`first_message`	No	The greeting callers hear.
`inbound_prompt`	No	Instructions for incoming calls.
`idempotency_key`	Yes	Required to make the change. Repeating a key returns the first outcome instead of running the change again.
`outbound_prompt`	No	Instructions for outgoing calls.
`transfer_enabled`	No	Whether the agent may transfer calls to a person.
`voice_catalog_id`	No	Voice to use: an id from list_voices. Preferred over voice.
`extraction_schema`	No	Fields to capture from each call.
`queue_for_approval`	No	When approval is missing, create a pending approval the owner can accept in the dashboard instead of returning needs_approval.
`transfer_phone_number`	No	Where transfers go (E.164).
`outbound_first_message`	No	Opening line on outgoing calls.

Output Schema

Name	Required	Description
`code`	No
`error`	No	Present when success is false
`intent`	No
`result`	No
`status`	No
`message`	No
`success`	Yes	Whether the tool completed successfully
`summary`	No
`approval`	No
`request_id`	No
`risk_level`	No
`business_id`	No
`missing_fields`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 12, 2026

changedInput schema / properties / actor / description

Previous value: -"Who is asking: { type: agent|human|system|integration, id, display_name }."New value: +"Do not set. Kept for older clients; the signed-in connection identifies you."

changedInput schema / properties / authority / description

Previous value: -"How the owner approved this exact change: { mode: 'human_confirmed', confirmed_by, confirmed_at, confirmation_ref }. Without it the result is needs_approval and nothing changes."New value: +"Do not set. It cannot approve a change: the owner approves through review_url or by being signed in."

addedInput schema / properties / voice_catalog_id

Added value: +{
+  "description": "Voice to use: an id from list_voices. Preferred over voice.",
+  "type": "string"
+}

First observedNov 12, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true; the description adds real context beyond them, notably the user-visible effect ('Callers hear the change on their next call') and the full outcome vocabulary with the warning that 'only executed means the change was made'. It does not spell out how the owner actually grants approval (review_url appears only in the schema) or whether an executed change is reversible, which keeps it short of a 5.

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?

Four tight sentences: purpose first, prerequisites second, runtime effect third, return statuses last. Nothing is padding, though the field list and status list are dense and the idempotency/approval prerequisites partially duplicate schema text.

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 25-parameter destructive mutation with an output schema, the description covers the decision criteria, the visible side effect and the terminal statuses an agent must branch on. The remaining gap is the mechanics of obtaining approval (review_url) and behavior when approval is denied or unsupported beyond the status name.

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% across 25 parameters, so the schema carries the detail; the description only restates the agent_id requirement, the 'at least one field' rule and the approval requirement. It adds the useful 'at least one change field' constraint but no syntax or interaction details beyond the schema, 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 plus resource ('Change a live agent's...') and enumerates the exact changeable fields (name, greeting, prompts, voice, model, call length, call transfer). It also explicitly distinguishes itself from the sibling update_agent_config, so an agent can pick correctly without opening either 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 precise condition for this tool ('changes made on the owner's behalf that need a recorded approval') and names the alternative path for the other case ('Direct edits by the owner go through update_agent_config'). Prerequisites (agent_id, at least one field, confirmed owner approval) are stated up front.

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

All CallMCP — Phone Call MCP Server 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.