CallMCP — Phone Call MCP Server

Rollback Agent Configuration

rollback_config

DestructiveIdempotent

Request a rollback to a saved version of the agent settings. It restores the version's greeting, voice, prompt (and the editable prompt copy, when the version saved one), model and call summary/scoring. Transfer settings, call length, tools and speech recognition stay as they are; the result lists what was and was not restored. When the business owner or an admin is signed in through this connector, the rollback applies immediately; otherwise the owner approves it from a review link. Targets are listed by list_config_versions. The rollback is itself saved as a new version, and secrets are never copied.

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>"
    },
    "name": "rollback_config"
  }
}

Input Schema

Name	Required	Description
`actor`	No	Do not set. Kept for older clients; the signed-in connection identifies you.
`reason`	No	Optional human-readable reason recorded in the audit trail.
`dry_run`	No	Validate tenant, scope, and policy without touching the live config.
`agent_id`	Yes	Agent ID 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	External source reference, such as a ticket or automation run ID.
`version_id`	No	Version id to restore, from list_config_versions. One of version_number/version_id is required.
`business_id`	No	Business ID (optional only when the token can access exactly one business).
`version_number`	No	Version number to restore, from list_config_versions. One of version_number/version_id is required.
`idempotency_key`	No	Stable key for this rollback; repeating it returns the first outcome. Defaults to a key from the agent, the target version and the version live now, so rolling back to the same version again after later changes works. The result returns the key used.
`queue_for_approval`	No	Create a durable owner-review request (default true). Setting false returns needs_approval, but an authority-envelope retry still cannot execute.

Output Schema

Name	Required	Description
`code`	No
`error`	No	Present when success is false
`result`	No	On executed: { agent_id, restored_from_version, restored_fields, skipped_fields, not_restored, new_version_number, warning? }.
`status`	No
`message`	No
`success`	Yes	Whether the tool completed successfully
`summary`	No
`agent_id`	No
`approval`	No
`request_id`	No
`risk_level`	No
`business_id`	No
`idempotency_key`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 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: -"Attribution only. Caller-supplied modes cannot authorize a rollback; authenticated owner review of the exact stored request is required."New value: +"Do not set. It cannot approve a change: the owner approves through review_url or by being signed in."

changedInput schema / properties / idempotency_key / description

Previous value: -"Stable key for the rollback request; repeating it returns the original outcome. Defaults to a key derived from agent + version — a fresh key repeats a rollback that already executed."New value: +"Stable key for this rollback; repeating it returns the first outcome. Defaults to a key from the agent, the target version and the version live now, so rolling back to the same version again after later changes works. The result returns the key used."

changedInput schema / properties / version_id / description

Previous value: -"Target assistant_config_versions row id to restore. One of version_number/version_id is required."New value: +"Version id to restore, from list_config_versions. One of version_number/version_id is required."

changedInput schema / properties / version_number / description

Previous value: -"Target assistant_config_versions.version_number to restore. One of version_number/version_id is required."New value: +"Version number to restore, from list_config_versions. One of version_number/version_id is required."

addedOutput schema / properties / idempotency_key

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / result / description

Previous value: -"On executed: { agent_id, restored_from_version, restored_fields, skipped_fields, new_version_number, warning? }."New value: +"On executed: { agent_id, restored_from_version, restored_fields, skipped_fields, not_restored, new_version_number, warning? }."

First observedNov 12, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Beyond the annotations, the description discloses the precise restoration scope, the fields intentionally left untouched, that the result lists what was and was not restored, that the rollback is saved as a new version, and that secrets are never copied. It also explains the approval behavior and the owner-review link. This is rich behavioral context that materially helps an agent predict consequences.

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?

The description is front-loaded with the action and restoration scope, then adds exclusions, approval behavior, and versioning consequences in a compact sequence. Every sentence contributes operational detail, and there is no filler.

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?

Given the destructive and idempotent annotations, a rich 11-parameter schema, and an output schema, the description supplies the remaining critical context: what gets restored, what stays, approval flow, and that secrets are not copied. An agent has enough information to call the tool correctly and understand the likely outcome.

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%, so parameter meaning is already fully documented. The description reinforces that version targets come from list_config_versions, but that is largely duplicative of the schema. With the schema doing the heavy lifting, a baseline 3 is appropriate.

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?

The description gives a specific verb and resource: rollback the agent settings to a saved version. It clearly enumerates which fields are restored and which are left unchanged, making the effect concrete. It does not explicitly contrast itself with the sibling request_config_rollback, so sibling differentiation is incomplete.

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?

It states the required workflow step: version targets come from list_config_versions. It also explains the two execution paths, immediate application when an owner or admin is signed in versus owner approval through a review link, which tells the agent what outcome to expect. It does not name when to choose this over request_config_rollback or update_agent_config, but the usage context is otherwise clear.

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.