Skip to main content
Glama
Sign In

CallMCP — Phone Call MCP Server

by ai.callmcp
OverviewDiscussionsAdmin

Run Installation Test Scenarios

agency_installation_run_scenarios
DestructiveIdempotent

Run approved verification scenarios for an existing client installation at its expected revision using voice agent compute under existing entitlement. Requires current assigned client authority, current owner approval and evals:write. Saves test evidence and can incur irreversible usage charges; a new request key can run and charge again. Makes no real customer calls.

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>",
      "requestId": "<requestId>"
    },
    "name": "agency_installation_run_scenarios"
  }
}

Input Schema

NameRequiredDescriptionDefault
partnerIdYesThe agency (partner) workspace ID.
requestIdYesA stable ID for this run; reuse it to continue the same run.
installationIdYesThe agency package installation to act on.
expectedRevisionYesThe installation revision you last read. The call is rejected if the installation has changed since.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent when success is false
receiptNo
successYesWhether the tool completed successfully

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true, openWorldHint=true, idempotentHint=true), it explains that the run saves test evidence, can incur irreversible usage charges, and that a new request key can run and charge again. It also negates a false assumption by stating no real customer calls are made despite openWorldHint. This is exactly the cost/irreversibility context annotations cannot convey.

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?

Two sentences, zero filler: purpose and scope first, then requirements, side effects, and the no-real-calls caveat. Every clause carries information an agent needs before invoking.

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 an output schema exists, return values need no explanation, and the description covers the remaining gaps for a destructive, chargeable, open-world tool: authority requirements, revision pinning, evidence persistence, billing repeat-charge risk, and the fact that no real customer traffic is generated.

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; the description exceeds it by tying requestId to billing semantics ('a new request key can run and charge again') and framing expectedRevision as the pin against drift. That adds decision-relevant meaning beyond the schema's 'reuse it to continue the same run.'

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 and resource: run approved verification scenarios for an existing client installation at its expected revision, using voice agent compute under existing entitlement. It distinguishes itself from the sibling mutation tools (apply_update, approve_*, offboard) by being a verification/test run at a pinned revision, so an agent can select it without 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?

It states the preconditions for use (existing installation, approved scenarios, expected revision, assigned client authority, owner approval, evals:write) and clarifies scope with 'Makes no real customer calls.' It does not explicitly route to an alternative such as run_eval or say when not to use it, so it falls short of a 5.

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 toolsInspect
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