Skip to main content
Glama

AceRound AI Interview Copilot

update_interview_preference

Update interview preferences (synced across devices and used as defaults when starting an interview). Pass only what changes; everything else stays. Current values via get_settings; knowledge base IDs from list_knowledge_bases and list_official_knowledge_bases. Save a full custom prompt with save_custom_prompt. (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_interview_preference"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoInterview language
altLangsNoOther languages the user can switch to during the interview; empty = single language
webSearchNoAllow web search during live interviews
answerStyleNoAnswer style: keypoints / answerOnly / natural / structured
enableReplayNoInterview replay (records the user’s answers; when off the microphone is never used)
customDataIdsNoKnowledge base IDs attached by default (replaces the list)
translateLangNoTranslation language; auto = automatic
dualLangAnswerNoAnswer in two languages
customAnswerStyleNoExtra answer requirements

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Goes well past the annotations (readOnly=false, destructive=false, openWorld=false) by disclosing cross-device sync, the persisted-defaults effect on future interviews, merge-not-replace semantics, and the required auth scope 'interviews:write'. It does not say what happens when an unknown knowledge base ID is passed or whether the response echoes the merged settings, so it stops short of full behavioral coverage.

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

Conciseness5/5

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

Three tight sentences plus a parenthetical auth note, front-loaded with the effect of the call, then the partial-update rule, then the dependency pointers. No filler and nothing repeated from the schema.

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 9-parameter, all-optional mutation with no output schema, the definition covers partial-update semantics, ID sourcing, prompt alternatives, and authorization. The remaining gap is the return contract — whether updated preferences come back or the agent must re-call get_settings to confirm.

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; the description earns above that by clarifying that omitted fields are preserved rather than reset — a real ambiguity given all 9 params are optional — and by pointing to the sibling that supplies valid customDataIds. It still doesn't disambiguate customAnswerStyle from save_custom_prompt beyond naming the latter.

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 interview preferences') and immediately scopes it: synced across devices, used as defaults when starting an interview. That framing separates it from session-level siblings like set_live_interview_options or start_interview without the agent opening a schema.

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?

Explicit routing: 'Pass only what changes' for partial updates, 'Current values via get_settings' for reads, 'knowledge base IDs from list_knowledge_bases and list_official_knowledge_bases' for IDs, and 'Save a full custom prompt with save_custom_prompt' as the alternative for the prompt case. When-to-use and which-sibling-to-use are both stated.

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