Skip to main content
Glama

AceRound AI Interview Copilot

start_interview

Destructive

Start a live or mock interview for the user and return the interview page link for the user to open in a browser (web only; it does not launch the desktop app; the user must be signed in to the same account in that browser). Live: the user shares the meeting tab with audio as prompted and, after clicking "Start interview", minutes are deducted by time online. Mock: one mock interview credit is deducted on creation. Only one session of each type can be in progress. Advanced settings not given (answer style, custom instructions, translation, answer recording, web search, knowledge bases) follow the user's saved interview preferences. Target IDs come from list_interview_targets, resume IDs from list_resumes. 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": {
      "targetId": "<targetId>",
      "resumeId": "<resumeId>"
    },
    "name": "start_interview"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoInterview language (selects the speech recognition model); omit to use the user's preference
modeNoLive only: online = video meeting (captures meeting audio), phone = phone interview (speakerphone picked up by the microphone; needs an enrolled voiceprint; Chinese / Cantonese / English only)online
typeNoINTERVIEW = live interview, MOCK_INTERVIEW = mock interviewINTERVIEW
focusNoMock only: what this session should focus on
roundNoLive only: which round this is for the target
resumeIdYesResume ID
targetIdYesTarget ID
skipIntroNoMock only: skip the self-introduction
assistModeNoMock only: turn on AI assist (a suggested answer for each question)
difficultyNoMock only: seniority levelFRESH_GRADUATE
extraLangsNoLive only: other languages the user may switch to during the interview; omit to use the user's preference
basicsRatioNoMock only: share of fundamentals questions, 0–100; omit to let the AI decide
questionCountNoMock only: number of questions; omit to let the AI decide
knowledgeBaseIdsNoKnowledge base IDs; for live interviews omit to use the user's preference; for mock interviews they apply only with AI assist on

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false; the description justifies that by disclosing that live sessions burn minutes by time online, mock sessions deduct a credit at creation, and a payment may be created. It also discloses the one-session-per-type concurrency limit and the interviews:write scope requirement — real context beyond what annotations convey.

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

Conciseness4/5

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

Front-loaded with purpose and return value, then cost and prerequisites. The nested parenthetical about scope and sign-in is dense and slightly run-on, but nearly every clause carries information an agent needs before calling a destructive, cost-incurring tool.

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?

For a 14-parameter, destructive, credit-consuming tool with no output schema, the description covers the return value (page link), cost model, concurrency constraint, auth scope, defaults for omitted parameters, and ID sources — nothing material is missing.

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, but the description adds meaningful semantics the schema does not: any advanced settings omitted fall back to the user's saved preferences, and omitted targetId/resumeId values must come from the list_* tools. It does not explain individual enums, but the schema already does.

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?

States a specific verb and resource ('Start a live or mock interview') plus the concrete outcome ('return the interview page link'), which distinguishes it from siblings like answer_mock_interview or start_exam that operate on an existing session.

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

Usage Guidelines5/5

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

Explicitly scopes usage (web only, does not launch the desktop app, user must be signed into the same account in that browser) and routes prerequisite lookups to list_interview_targets and list_resumes. It also imposes a required behavioral step: tell the user the cost and get agreement before invoking.

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