Skip to main content
Glama

AceRound AI Interview Copilot

solve_screen_question

Destructive

Have the user's running page capture the user's screen now and solve the question, same as the "Solve from screenshot" button / hotkey; charged by the current mode and page count, with the answer shown on the user's page. The AI assistant does not (and cannot) supply the image. Runs in the desktop assessment overlay when the user is in an assessment (it must have started); otherwise in screenshot solving on the live / mock interview page (the web page must be sharing the screen). 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": "solve_screen_question"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only flag readOnlyHint=false and destructiveHint=true; the description supplies the far more actionable risk detail: it consumes paid minutes/credits or creates a payment order, so the user must be told the price and consent first. It also discloses the auth prerequisite (sign-in with interviews:write scope) and that the answer surfaces on the user's page rather than being returned to the agent.

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 core action and its UI equivalent are front-loaded in the first clause, and every sentence carries distinct information (image sourcing, environment branching, billing consent, auth scope). It is dense with stacked parentheticals, which makes it slower to parse than necessary for a zero-parameter 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 no-param, no-output-schema tool, everything an agent needs is present: environment gating, auth scope, cost/consent obligations, and where the result appears given no return value. Nothing material is left to inference.

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?

The tool takes no parameters, so there is nothing to disambiguate; a 4 baseline applies. The description's note that the caller cannot pass an image usefully reinforces why the schema is empty.

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 action chain: the user's page captures the screen now, then the tool solves the question, and it anchors that to a known UI affordance (the "Solve from screenshot" button / hotkey). It also clarifies the non-obvious boundary that the AI assistant cannot supply the image, so an agent cannot mistake it for an image-input tool.

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 preconditions for both operating contexts: the desktop assessment overlay when an assessment has started, otherwise screenshot solving on a live/mock interview page that must already be screen-sharing. It also instructs the agent to disclose cost and obtain user agreement first. The one gap is that it never says when to prefer this over the similarly named sibling follow_up_screen_question.

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