Skip to main content
Glama

Duck Debate

duck_debate
Read-only

Run structured multi-round debates between AI providers in Oxford, Socratic, or adversarial formats to compare perspectives and synthesize a decision.

Instructions

Structured multi-round debate between ducks. Supports oxford (pro/con), socratic (questioning), and adversarial (attack/defend) formats.

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>",
      "format": "<format>"
    },
    "name": "duck_debate"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatYesDebate format: oxford (pro/con), socratic (questioning), adversarial (attack/defend)
promptYesThe debate topic or proposition
roundsNoNumber of debate rounds (default: 3)
providersNoProvider names to participate (min 2, uses all if not specified)
synthesizerNoProvider to synthesize the debate (optional, uses first provider)

Output Schema

NameRequiredDescriptionDefault
topicYes
formatYes
roundsYes
synthesisYes
synthesizerYes
totalRoundsYes
participantsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.20.14
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedOutput schema / properties / rounds / items / items / properties / error
      Added value: +{
      +  "type": "string"
      +}
  2. Addedv1.19.6
  3. Removedv1.19.5
  4. Changed5 schema fields changedv1.2.3
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / providers / items / enum
      Added value: +[
      +  "openai",
      +  "google",
      +  "groq",
      +  "ollama"
      +]
    • addedInput schema / properties / synthesizer / enum
      Added value: +[
      +  "openai",
      +  "google",
      +  "groq",
      +  "ollama"
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "format": {
      +      "enum": [
      +        "oxford",
      +        "socratic",
      +        "adversarial"
      +      ],
      +      "type": "string"
      +    },
      +    "participants": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "nickname": {
      +            "type": "string"
      +          },
      +          "position": {
      +            "enum": [
      +              "pro",
      +              "con",
      +              "neutral"
      +            ],
      +            "type": "string"
      +          },
      +          "provider": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "provider",
      +          "nickname",
      +          "position"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "rounds": {
      +      "items": {
      +        "items": {
      +          "additionalProperties": false,
      +          "properties": {
      +            "content": {
      +              "type": "string"
      +            },
      +            "nickname": {
      +              "type": "string"
      +            },
      +            "position": {
      +              "enum": [
      +                "pro",
      +                "con",
      +                "neutral"
      +              ],
      +              "type": "string"
      +            },
      +            "provider": {
      +              "type": "string"
      +            },
      +            "round": {
      +              "type": "number"
      +            }
      +          },
      +          "required": [
      +            "round",
      +            "provider",
      +            "nickname",
      +            "position",
      +            "content"
      +          ],
      +          "type": "object"
      +        },
      +        "type": "array"
      +      },
      +      "type": "array"
      +    },
      +    "synthesis": {
      +      "type": "string"
      +    },
      +    "synthesizer": {
      +      "type": "string"
      +    },
      +    "topic": {
      +      "type": "string"
      +    },
      +    "totalRounds": {
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "topic",
      +    "format",
      +    "totalRounds",
      +    "participants",
      +    "rounds",
      +    "synthesis",
      +    "synthesizer"
      +  ],
      +  "type": "object"
      +}
  5. First observedv1.0.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description is consistent with a non-mutating LLM orchestration call. It adds the multi-round structure, but says nothing about the practical behavior that matters here: that multiple providers mean multiple billed model calls, possible latency, or what happens when rounds is raised. With annotations covering safety, a 3 is fair.

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?

Two short sentences, front-loaded with the core action and followed by the format taxonomy; no filler. It is arguably too terse for a five-parameter multi-provider orchestrator, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the schema fully covers the inputs. However, for a tool that fans out to several providers over up to ten rounds, the description omits cost/latency implications and any steering on choosing formats, leaving the agent with only a surface-level understanding.

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 description coverage is 100%, so the schema already documents every parameter including enums, defaults and the minItems=2 constraint on providers. The description only restates the format list, which duplicates the enum description in the schema rather than adding new meaning. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('structured multi-round debate between ducks') and enumerates the three formats, so the agent knows exactly what the tool produces. It does not distinguish itself from near-neighbors such as compare_ducks or duck_council, leaving that separation implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives, even though siblings like duck_council, duck_vote, duck_judge and compare_ducks all involve multiple ducks reasoning together. The format names hint at intent but nothing tells an agent which tool to pick for a given task.

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