Skip to main content
Glama

AceRound AI Interview Copilot

ask_live_interview

Destructive

Ask a question in the live interview in progress on the user's behalf: the text is treated as the interviewer's question and answered on the interview page; if the AI is answering, that answer is interrupted first. Uses the same path as "Voice ask" in the desktop app and requires the user to have clicked "Start interview". Billed by time online. Requires the user to have this session open in the browser or desktop app and connected; the page carries it out exactly as if the user clicked the matching button. Uses the user's minutes or credits or creates a payment; tell the user what it costs and get their agreement first. (Requires the user's sign-in with scope interviews:write.)

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": {
      "question": "<question>"
    },
    "name": "ask_live_interview"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYesThe question

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

The description adds substantial behavior beyond annotations: an in-flight AI answer is interrupted first, the action is executed by the live page exactly as a button click, it is billed by time online, and it may spend minutes/credits or create a payment requiring user consent plus interviews:write auth. These details agree with destructiveHint=true and openWorldHint=false rather than contradicting them. However, the annotation already flags a destructive, non-read-only operation, and the description never states what comes back on success or failure, so the added value is real but incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The action and its core consequence are front-loaded in the first sentence, which is good. But the remainder is a long semicolon-chained block with overlapping claims — "same path as Voice ask" and "page carries it out exactly as if the user clicked the matching button" say nearly the same thing — and the auth scope is buried in parentheses at the end rather than surfaced as a precondition.

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 single-parameter action on a live external session, the description covers prerequisites, cost/consent obligations, auth scope, and the side effect of interrupting an ongoing answer. With no output schema, the omission of any statement about the result of the call is the main remaining gap, but everything needed to invoke it safely is present.

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 coverage is 100% for the single parameter, including length bounds, so the schema already carries the specification. The description adds a framing nuance — the text is interpreted as the interviewer's question, not as an instruction to the assistant — which is genuinely useful. Beyond that it adds no format, language, or phrasing guidance, so the 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?

The first clause names a specific verb and resource: ask a question in the live interview in progress, on the user's behalf, with the text treated as the interviewer's question. That is far more than a restatement of the name. It does not explicitly name a sibling to distinguish itself from (e.g. answer_live_interview_now), though the interrupt semantics imply the boundary.

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 concrete preconditions for use: the user must have clicked "Start interview", must have the session open in the browser or desktop app, and must be connected. It also requires telling the user the cost and getting agreement first. What is missing is an explicit "use X instead when…" routing against siblings such as answer_live_interview_now or interrupt_live_interview_answer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources