CallMCP — Phone Call MCP Server

Request Agent Rollback With Approval

request_config_rollback

DestructiveIdempotent

Put a live agent back on a saved earlier version of its configuration (listed by list_config_versions), with the owner's confirmed approval. Replaces the current live configuration; callers hear the restored version on their next call. Needs agent_id and version_number or version_id. 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_config_rollback"
  }
}

Input Schema

Name	Required	Description
`actor`	No	Do not set. Kept for older clients; the signed-in connection identifies you.
`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.
`agent_id`	Yes	The agent to roll back.
`authority`	No	Do not set. It cannot approve a change: the owner approves through review_url or by being signed in.
`source_ref`	No	Optional reference for the request, such as a ticket or automation run ID.
`version_id`	No	Or the saved version id.
`business_id`	No	Business ID. Required when the token can reach more than one business.
`version_number`	No	The saved version to restore.
`idempotency_key`	Yes	Required to make the change. Repeating a key returns the first outcome instead of running the change again.
`queue_for_approval`	No	When approval is missing, create a pending approval the owner can accept in the dashboard instead of returning needs_approval.

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.

Changed2 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."

First observedNov 12, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare destructive=true and idempotent=true, and the description adds real value on top: the current live configuration is replaced, callers hear the restored version on their next call, and only an 'executed' outcome means the change actually happened. It does not discuss permission requirements or rate limits, keeping it short of the top band.

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?

Three tight sentences, front-loaded with the action and its precondition, followed by the side effect and the outcome vocabulary. No filler or restatement of the name.

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 destructive, idempotent mutation with 11 parameters and nested objects, the description covers the action, the precondition, the observable effect and the outcome states. An output schema exists, so return-value detail need not be repeated.

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 100%, so the baseline is 3, but the description adds the non-obvious either/or relationship between version_number and version_id, which the required-parameter list alone does not convey. It leaves the approval, dry-run and idempotency semantics to the schema descriptions.

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 precise verb and resource (restore an agent to a saved configuration version) plus the distinguishing condition that this path is approval-gated by the owner. It also names list_config_versions as the discovery step, so an agent can tell what this does before opening the schema.

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?

The description gives a clear usage context: roll back a live agent to an earlier saved version, discovered via list_config_versions, and only after the owner confirms. It does not spell out when not to use it (e.g., the non-approval path or when no saved versions exist), so an explicit exclusion is missing.

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.