Skip to main content
Glama

AceRound AI Interview Copilot

update_client_settings

Update the desktop client’s cloud settings (hotkeys, overlay style, modes, auto-answer, silence gate, disguise, theme…). Pass only what changes; overlayStyle, actionHotkeys and disguise are merged by key. Current values via get_settings. The client applies cloud settings on its next launch or sign-in; if the user changes any setting locally before that, the local copy wins. (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": "update_client_settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNoTheme: system / light / dark
localeNoUI language; null follows the system
uiScaleNoMain window UI scale
disguiseNoCustom process name and window title, merged by key
examModeNoExam mode: instant / quick / programming
turnCardsNo
autoAnswerNoAnswer automatically when the interviewer finishes; when off, only on “Answer now”
answerFirstNo
audioSourceNoInterview type: SPEAKER online (system audio) / PHONE phone interview (microphone)
newestFirstNo
panicHotkeyNoPanic hide hotkey
hotkeySchemeNoDefault hotkey scheme for actions not set individually: simple / conflict-free
overlayStyleNoOverlay style, merged by key: theme, interviewBgOpacity / examBgOpacity (0–1), interviewTextOpacity / examTextOpacity (0–1), interviewBorderOpacity / examBorderOpacity, fontScale (0.3–4), textBold, textHalo, scrollSpeed (0.05–5), hotkeyOpacityStep, examSolveHoverMs, interviewWidth / interviewHeight / examWidth / examHeight (pixels)
actionHotkeysNoOverlay action hotkeys, merged by key; values are Tauri accelerators such as CommandOrControl+Shift+Enter. Actions: answer capture voice-ask scroll-up scroll-down move-left move-right move-up move-down copy-code size-up size-down opacity-up opacity-down text-opacity-up text-opacity-down auto-palette restore-palette
nativeExamOsdNo
silenceGateMsNoHow long the interviewer must pause before the question counts as finished (ms, 300–6000)
examDualCameraNo
followNewRoundNo
solverExamModeNoMode for screenshot answers during interviews: instant / quick / programming
followStreamingNo
hideFromTaskbarNo
showHotkeyHintsNo
autoOpenMockShellNo
showExamReasoningNo
showCopyCodeButtonNo
interviewDualCameraNo
overlayStylePresetsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare a non-destructive write; the description goes well beyond them by disclosing merge-by-key semantics for overlayStyle, actionHotkeys and disguise, the deferred application model ('next launch or sign-in'), the conflict rule that local changes win, and the required auth scope interviews:write. These are exactly the non-obvious traits an agent needs before mutating settings.

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?

Three tight sentences, front-loaded with the action and the partial-update rule, followed by merge semantics, timing and auth. The parenthetical field enumeration is mildly redundant with the schema, but it usefully signals scope in one glance.

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 27-param mutation with no output schema, the description covers the hardest parts correctly: merge behavior, when changes take effect, and the auth prerequisite. It stops short of saying what the call returns or what the many undocumented boolean toggles mean, which is a real but secondary gap.

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?

With 27 parameters and only 48% schema description coverage, the description compensates for the object params by explaining key-level merging for the three nested structures, and the parenthetical field list maps loosely onto several top-level names. But roughly a dozen boolean flags (turnCards, answerFirst, newestFirst, nativeExamOsd, followStreaming, overlayStylePresets, etc.) are unexplained in both the schema and the description, so the gap is only partly filled.

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 ('Update the desktop client's cloud settings') and enumerates representative fields (hotkeys, overlay style, modes, auto-answer, silence gate, disguise, theme), which lets an agent distinguish it from the sibling get_settings reader without opening the schema.

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 operational context: 'Pass only what changes' establishes partial-update semantics, and 'Current values via get_settings' routes the agent to the sibling for reads. It does not, however, address adjacent siblings like update_exam_customization or update_interview_preference, so an agent cannot tell from this text whether some of these settings belong in those tools instead.

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