CallMCP — Phone Call MCP Server

Answer Call Question

answer_call_question

Idempotent

Send the person's answer to a live call's pending_question, or decline. Send only what they said; answered once.

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": {
      "call_id": "<call_id>"
    },
    "name": "answer_call_question"
  }
}

Input Schema

Name	Required	Description
`answer`	No	The person's answer, in their words (required unless decline is true)
`call_id`	Yes	The KaiCalls call ID from make_call
`decline`	No	True when the person does not want to share this (optional)
`question_id`	No	The pending_question.question_id to answer (optional; defaults to the oldest open question)

Output Schema

Name	Required	Description
`code`	No
`error`	No	Present when success is false
`call_id`	No
`success`	Yes	Whether the tool completed successfully
`replayed`	No
`question_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare non-read-only, open-world, idempotent, non-destructive behavior. The description adds real context beyond that: 'Send only what they said' constrains answer fidelity (verbatim, no paraphrasing), and 'answered once' explains the single-answer semantics behind idempotency. It does not cover failure modes such as an already-answered or expired question, which keeps it from 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core action front-loaded and the constraint follow-up earning its place. No filler, no restatement of the title.

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?

Output schema exists and all four parameters are documented, so the description only needs to carry behavioral intent — which it does via verbatim-answer and once-only rules. The remaining gap is what happens when the question is no longer open or the call has ended, a realistic concern for a live-call write tool.

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 the schema already documents answer, call_id, decline, and question_id including the default-to-oldest behavior. The description reinforces that answer should be verbatim and that decline is a substitute, but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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?

States a specific verb and resource: send the person's answer to a live call's pending_question, with a decline path. An agent can distinguish this from call-lifecycle siblings like make_call or check_call_status. It stops short of naming an alternative tool, but the action itself is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the phrase 'live call's pending_question', which signals the prerequisite state for calling this tool. The 'or decline' branch describes an in-tool option rather than routing to a different tool. No explicit when-not guidance or prerequisites (e.g., question must still be open) are stated.

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.