Skip to main content
Glama

AceRound AI Interview Copilot

start_question_prediction

Destructive

Predict the questions most likely to come up for one of the user’s target roles, with answer outlines drawn from their resume. Generation takes about 30–90 seconds; the record is saved only when it succeeds. Uses 1 prediction credit on success (PRO is not charged; nothing is charged on failure). If it is still running when this call returns, check list_question_predictions a little later: a new record means it finished; no new record after a few minutes means it failed and nothing was charged. 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": {
      "goalId": "<goalId>"
    },
    "name": "start_question_prediction"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoOutput language name, e.g. English, Simplified Chinese; defaults to the user interface language
countNoNumber of questions
goalIdYesTarget role ID
resumeIdNoResume ID from list_resumes; omit to base it on the role only
experienceNoExperience level: Entry-level / 1-3 years / 3-5 years / 5-10 years / 10+ years

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, it discloses the 30–90 second runtime, success-only persistence, one-credit charge on success, no charge on failure, and how to determine completion via list_question_predictions. It also states the required sign-in scope and the need to obtain user agreement for costs.

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 is front-loaded and the operational details follow in a logical order: runtime, persistence, billing, status-check fallback, and authorization. The cost-and-consent sentence is slightly dense, but the length is justified for an asynchronous charged generation 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 charged asynchronous operation with no output schema, the description covers what is generated, how long it takes, when results are saved, how to verify completion, billing behavior on success and failure, and authentication requirements. An agent has enough information to call it correctly and explain the outcome to the user.

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 coverage is 100%, so the input schema already documents all five parameters including language, count, role ID, resume ID, and experience. The description adds useful context that answer outlines are drawn from the resume and the role, but it does not add parameter-level semantics beyond the schema.

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?

The description states a specific verb and resource: predict likely interview questions for a target role, with answer outlines from the resume. It clearly frames the output and the data source, so the agent can distinguish this generation action from listing or retrieving predictions.

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?

It explains when to check status via list_question_predictions if the call returns while still running, and what a new or missing record means. It also gives the consent requirement before spending credits, though it does not explicitly compare against other generation-style siblings such as start_interview.

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