Skip to main content
Glama

AceRound AI Interview Copilot

start_exam

Destructive

Start an assessment on the user's computer, exactly like clicking "Start assessment" on the assessment page of the desktop app: starts with the given answer mode and role, opens the assessment overlay and tucks away the main window. Requires the desktop app to be running and signed in on the user's computer; if it is offline, an older version, short on balance, or an interview or assessment is already in progress, the reason is returned and nothing starts. Starting is free; each screenshot solved afterwards deducts the user's minutes by the chosen mode. Once started, the user uses the overlay on the assessment page as usual; solve_screen_question can also capture and solve. The assessment record is created on the first solved screenshot and can then be seen with list_exams. 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

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_exam"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoAnswer mode: instant = Instant mode(2 minutes per screenshot); quick = Quick mode(2 minutes per screenshot); programming = Coding mode(5 minutes per question). Members are not charged minutes. Omit to keep the mode currently selected on the assessment page of the app
goalIdNoRole (target) ID to link, from list_interview_targets; null = no role. Use either this or jobName; omit both to keep the role currently filled in on the assessment page of the app
jobNameNoName of a new role, when the user has not saved it yet; it is created on start (same as typing a role on the assessment page)
companyNameNoCompany of the new role, given with jobName

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the annotations: it enumerates the failure reasons that abort the start (offline, outdated version, insufficient balance, another session in progress), discloses that starting is free while each solved screenshot deducts minutes, and notes the record only materializes on the first solved screenshot. It also names the required OAuth scope (interviews:write), which the annotations do not 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?

The purpose and the UI equivalence are front-loaded, then prerequisites, cost, and downstream effects follow in a sensible order. It is a single dense paragraph with some repetition ("assessment page" twice, "as usual" filler), but nearly every sentence carries operational information.

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 multi-effect, prerequisite-heavy tool with no output schema, the definition covers preconditions, billing consequences, record creation timing, permission scope, and follow-up tools. An agent has everything needed to decide whether to call it and what to warn the user about beforehand.

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 mode, goalId, jobName and companyName are already fully documented, including the omit-to-keep-current behavior. The description only restates "with the given answer mode and role" and adds no format or interaction detail beyond the schema.

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 ("Start an assessment on the user's computer") and anchors it to a concrete UI action ("exactly like clicking Start assessment on the assessment page of the desktop app"). It implicitly separates itself from interview flows ("an interview or assessment is already in progress") but never names start_interview as the alternative, so the sibling distinction is inferred rather than stated.

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 clear preconditions and usage context: the desktop app must be running and signed in, and the user must consume minutes/credits, so the caller is told to state the cost and obtain agreement first. It also points at solve_screen_question and list_exams as follow-ups. It stops short of explicit when-not routing versus start_interview or start_question_prediction.

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