Skip to main content
Glama

Chat with a Duck

chat_with_duck

Maintain conversation context while explaining problems to AI ducks for rubber-duck debugging. Send text or images and switch providers mid-conversation to gather different LLM perspectives.

Instructions

Have a conversation with a duck, maintaining context across messages

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": {
      "conversation_id": "<conversation_id>",
      "message": "<message>"
    },
    "name": "chat_with_duck"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoSpecific model to use (optional)
imagesNoOptional images to include with the message (for vision-capable models)
messageYesYour message to the duck
providerNoProvider to use (can switch mid-conversation)
conversation_idYesConversation ID (creates new if not exists)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.20.14
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / images / items / additionalProperties
      Removed value: -false
  2. Addedv1.19.6
  3. Removedv1.19.5
  4. Changed4 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 / images
      Added value: +{
      +  "description": "Optional images to include with the message (for vision-capable models)",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "data": {
      +        "description": "Base64-encoded image data",
      +        "type": "string"
      +      },
      +      "mimeType": {
      +        "description": "MIME type (e.g., \"image/png\") — required for base64 data, optional for URLs",
      +        "type": "string"
      +      },
      +      "url": {
      +        "description": "Image URL — passed directly to the LLM provider",
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / provider / enum
      Added value: +[
      +  "openai",
      +  "google",
      +  "groq",
      +  "ollama"
      +]
  5. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

The only annotation is openWorldHint=true, so the description must carry most of the behavioral burden. It does add one genuinely new fact — that context is maintained across messages (stateful behavior) — but says nothing about the external LLM provider dependency, latency/cost implications, or what happens when conversation_id is new versus existing.

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?

A single short clause, front-loaded with the core action and immediately followed by the distinguishing trait. Nothing is wasted, though the extreme brevity means little structure beyond one sentence.

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?

A single sentence for a five-parameter tool is thin, but the schema is fully documented (including images, provider enum, and conversation_id creation) and no output schema is needed. The main gap is that external-provider behavior and multi-turn semantics beyond the one clause go unmentioned; this is a minor rather than crippling omission.

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 every parameter including model, images, provider, and conversation_id is already documented in the schema. The description adds no additional meaning such as provider/model interaction or the semantics of switching providers mid-conversation, so the 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 and resource ('Have a conversation with a duck') plus a distinguishing trait, 'maintaining context across messages'. That trait implicitly separates it from one-shot siblings like ask_duck, but the description never names a sibling explicitly, so it falls short of a 5.

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

Usage Guidelines3/5

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

Usage is only implied: 'maintaining context across messages' hints that this is the multi-turn option rather than a one-shot query. There is no explicit when-to-use/when-not statement and no reference to ask_duck, duck_debate, or the other conversation-adjacent siblings, leaving the agent to infer routing.

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