Skip to main content
Glama

Ask K-EXAONE

ask_exaone
Read-only

Delegate a self-contained task or question to K-EXAONE 2.5 for an independent second opinion, a Korean-native draft or review, or offloading work, with optional local file attachments.

Instructions

Delegate a task or question to K-EXAONE 2.5 (LG AI Research) and return its answer.

Use it to get an independent second opinion, a Korean-native draft or review, or to offload a self-contained subtask. EXAONE cannot see your workspace, tools or this conversation: put every needed fact in prompt, or pass local text files with files (the server reads them itself, so their contents do not have to pass through your context). EXAONE is text-only and always reasons before answering. Higher reasoning_effort is slower and uses more tokens. To ask a follow-up in the same thread, pass the conversation_id printed at the end of the previous answer. The answer ends with a [k-exaone-mcp] footer showing token usage and remaining API rate limits.

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": {
      "prompt": "<prompt>"
    },
    "name": "ask_exaone"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesNoAbsolute paths of local UTF-8 text files to attach (code, docs, logs). Binary files are rejected.
promptYesInstruction or question for EXAONE. Be explicit; it has no other context.
systemNoOptional system prompt (role, output format). Only used when starting a new conversation.
max_tokensNoUpper bound for generated tokens INCLUDING reasoning. Leave unset unless you need a cap.
conversation_idNoContinue a previous conversation. Omit to start a new one.
reasoning_effortNolow (fast) / medium / high / max (deepest, slowest). Default: high.
include_reasoningNoAlso return EXAONE's reasoning trace (long). Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds far more — EXAONE cannot see the workspace, tools, or conversation; files are read server-side so contents need not enter the caller's context; the model is text-only and always reasons before answering; higher reasoning_effort costs latency and tokens; the response ends with a footer showing token usage and remaining API rate limits.

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?

Front-loaded with the core purpose, then layered with constraints in a logical order (context isolation, files, cost, threading, return format). Every sentence carries information, though the middle block is dense and could be tightened into a shorter list without losing content.

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?

With no output schema, the description still characterizes the return value (answer plus a token/rate-limit footer) and how to continue a thread. For a 7-parameter open-world delegation tool, the critical operational facts — context isolation, file handling, threading, cost — are all covered.

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, but the description adds real meaning: it explains that conversation_id comes from the footer printed at the end of the previous answer (not just 'continue a conversation'), that file contents are consumed server-side, and that reasoning_effort trades latency and tokens for depth.

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 — delegating a task or question to K-EXAONE 2.5 and returning the answer — with the provider named. The concrete scenarios (second opinion, Korean-native draft/review, offloading a self-contained subtask) make it unmistakable against the only sibling, exaone_status, which is clearly a status check.

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 when-to-use contexts: independent second opinion, Korean-native drafting/review, and offloading a self-contained subtask. It also implicitly scopes use by noting the subtask must be self-contained. What it lacks is an explicit exclusion or a pointer to the alternative tool (exaone_status) for non-delegation needs.

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

Deploy Server

Other Tools