AI Interview Questions MCP

Search questions

search_questions

Read-onlyIdempotent

Search interview questions by keywords and filter by track, topic, or level, returning question IDs to retrieve full model answers.

Instructions

Keyword search across questions and model answers. Optional track, topic and level filters. Returns question ids; use get_question for the full answer.

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": {
      "query": "<query>"
    },
    "name": "search_questions"
  }
}

Input Schema

Name	Required	Description
`level`	No
`limit`	No
`query`	Yes	Keywords, e.g. 'kv cache', 'rag evaluation', 'prompt injection'
`topic`	No	Topic id from list_topics
`track`	No	ai-engineer or investment-banking; omit to search both

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Nov 5, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description does add the non-obvious fact that model answers are indexed and that only ids come back, but says nothing about result ordering, the limit cap, or empty-result behavior.

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 short sentences, front-loaded with the core operation, then filters, then return shape and next step. No redundant restatement of the name or annotations.

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?

With no output schema, the description correctly states what comes back (question ids) and points to the follow-up tool. Only minor gaps remain around pagination and the limit default, which is adequate for a read-only search tool.

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 description coverage is 60% and enums self-document, so the bar is lower. The description still adds meaning by framing track, topic and level as optional filters that narrow a keyword search, though limit and its maximum are left to 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?

States a specific verb and resource ('keyword search across questions and model answers') and clarifies the search covers answer text, not just titles. It also distinguishes the result from the sibling get_question by noting that only question ids are returned.

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?

Explicitly routes the agent to get_question for full answers, which is the main follow-up decision after a search. It does not contrast with list_topics or random_question, so browsing versus searching is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server