Skip to main content
Glama
Sign In
llm-sparring

llm-sparring

by 121Development
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

Debate turn with GPT

debate_turn

Submit your rebuttal in an open debate to receive GPT's counter-rebuttal and current round status, so you can continue or proceed to verdict.

Instructions

Send your rebuttal in an open debate and get GPT's counter-rebuttal plus the round status. Call this after debate_open or a previous debate_turn, once you have written your rebuttal to GPT's last argument in the chat. Pass the same rebuttal text you showed the user. Respond to GPT's specific disagreements; concede points you can't defend. When no rounds remain, call debate_verdict instead.

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": {
      "debate_id": "<debate_id>",
      "rebuttal": "<rebuttal>"
    },
    "name": "debate_turn"
  }
}

Input Schema

NameRequiredDescriptionDefault
rebuttalYesYour (Claude's) rebuttal for this round.
debate_idYesThe debate_id returned by debate_open.

Output Schema

NameRequiredDescriptionDefault
modelYes
statusYes
debate_idYes
expires_atYes
gpt_parsedYesFalse if GPT ignored the reply format; its text is shown raw.
max_roundsYes
rounds_completedYes
rounds_remainingYes
gpt_disagreementsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.4/5.0
Behavior4/5

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

The description goes beyond the annotations by detailing the behavior of the output, explicitly stating that the agent will receive GPT's specific counter-rebuttal and the round status. This is valuable behavioral context for an agent that needs to formulate its subsequent response based on that information.

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?

While dense, every sentence provides critical operational context (timing, content, outcome, exit). It avoids unnecessary filler, though its length is required to convey the necessary multi-step state machine logic of a debate session.

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?

The definition is extremely complete for a complex conversational flow tool. It covers the input requirements, the execution flow, the expected result, and the logical transition to the end state, making it highly actionable for an AI agent.

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?

Since schema coverage is 100%, the description primarily serves to enforce workflow and content constraints (e.g., 'Pass the same rebuttal text you showed the user') rather than adding meaning to the formal data types. A baseline score is appropriate given the complete 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 tool's purpose is clearly defined as sending a user's rebuttal to initiate a debate turn and receiving GPT's counter-rebuttal and the current round status. This distinguishes it clearly as a state-transition and information retrieval step within a conversational debate framework.

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?

It provides highly specific usage guidelines, including required prerequisites ('after debate_open' or a previous 'debate_turn'), necessary preconditions ('once you have written your rebuttal'), and a clear alternative action ('When no rounds remain, call debate_verdict instead'). This prevents incorrect sequencing.

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