Skip to main content
Glama
Sign In

CallForMe

by tel.callforme
OverviewDiscussionsAdmin

Tell the assistant on the live call

answer_question
Destructive

Send a message into a live call; the assistant says it within a couple of seconds. Use it to answer pending_question (pass its question_id; the business is waiting, about 45 seconds), or anytime to change course: "Make it 6 people instead of 4", "Also ask if they price-match", "Don't book, just get the price", "Wrap up and hang up". An answer from what's already known is fastest; the user is the fallback. A late answer is still passed along.

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>",
      "answer": "<answer>"
    },
    "name": "answer_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
answerYesThe answer or instruction, e.g. "2019 Toyota RAV4" or "Yes, book 7:30"
call_idYesThe call_id from place_call
question_idNopending_question_id from get_call (e.g. "q2"). Leave out to answer the newest question, or to steer when no question is waiting.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, non-idempotent and open-world, so the safety bar is partly covered. The description adds valuable context beyond them: delivery latency (~seconds), the ~45-second window on pending questions, and that late answers are still relayed (non-idempotent, out-of-order effects). It stops short of saying whether a message can be retracted or what confirmation the caller receives.

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?

Front-loaded with the core action and effect, then usage cases, then fallback ordering. Every clause carries information (latency, deadline, examples, late handling) with no filler.

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?

For a 3-parameter mutation tool with no output schema, the description covers timing, urgency, and steering semantics well. What an agent receives back after sending (acknowledgement or error) is unstated, a minor gap given no output schema exists.

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%, and the schema already explains question_id (including the 'leave out to answer the newest question' behavior) and answer examples. The description reinforces the question_id use case and urgency but adds little syntax or format detail beyond the schema, so baseline 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?

Starts with a specific verb+resource ('Send a message into a live call') and states the observable effect ('the assistant says it within a couple of seconds'). This clearly separates it from siblings like get_call (read question) and hang_up (terminate).

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?

Gives explicit when-to-use cases: answering a pending_question (with the ~45s urgency) or steering mid-call, backed by concrete example phrasings. It also states a fallback ordering ('answer from what's already known is fastest; the user is the fallback'). It does not, however, address overlap with the sibling hang_up, despite using 'Wrap up and hang up' as an example instruction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All CallForMe 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