CallMCP — Phone Call MCP Server

Offboard Installation

agency_installation_offboard

DestructiveIdempotent

Starts offboarding: stops the package's jobs, revokes its future automation authority and turns off its scheduled reports. Requires the client owner, accepted set to true and the fingerprint from preview_offboard. The phone number, connections, billing plan and history are kept.

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": {
      "partnerId": "<partnerId>",
      "installationId": "<installationId>",
      "expectedRevision": "<expectedRevision>"
    },
    "name": "agency_installation_offboard"
  }
}

Input Schema

Name	Required	Description
`accepted`	No	Must be true to confirm the owner accepts the previewed effects.
`partnerId`	Yes	The agency (partner) workspace ID.
`fingerprint`	No	The fingerprint returned by the matching preview action.
`installationId`	Yes	The agency package installation to act on.
`expectedRevision`	Yes	The installation revision you last read. The call is rejected if the installation has changed since.

Output Schema

Name	Required	Description
`error`	No	Present when success is false
`receipt`	No
`success`	Yes	Whether the tool completed successfully

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is met by added context rather than restatement — and the description delivers exactly that by naming what is destroyed (jobs, automation authority, reports) and what survives (phone number, connections, billing plan, history). That survival list is the single most important behavioral fact for an agent about to run an irreversible operation.

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: the action and its effects first, then the invocation requirements, then the retention guarantee. No filler and the most decision-relevant information is front-loaded.

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?

An output schema exists so return values need no explanation, and annotations cover the safety profile. The description fills the remaining gap — the blast radius and the retained data — leaving nothing an agent needs in order to call this destructive operation correctly.

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 all five parameters are already documented in the input schema, including the fingerprint's origin and the expectedRevision rejection rule. The description restates the 'accepted' and fingerprint requirements without adding syntax, format, or edge-case meaning beyond the schema, so the baseline of 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?

Opens with a specific verb+resource ('Starts offboarding') and immediately enumerates the concrete effects: stops jobs, revokes future automation authority, disables scheduled reports. This distinguishes it clearly from the sibling agency_installation_preview_offboard, which shares the same domain but only previews.

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?

Explicitly states the preconditions for use: the client owner must act, 'accepted' must be true, and the fingerprint must come from preview_offboard, which effectively tells the agent to run the preview sibling first. It lacks an explicit when-not-to-use statement, but the prerequisite chain is clear enough to route correctly.

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.