Skip to main content
Glama

Compare Ducks

compare_ducks
Read-only

Send one prompt to multiple LLM providers simultaneously to compare responses and gather diverse perspectives; optionally include images for vision-capable models.

Instructions

Ask the same question to multiple ducks simultaneously

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": "compare_ducks"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoSpecific model to use for all providers (optional)
imagesNoOptional images to include with the prompt (for vision-capable models)
promptYesThe question to ask all ducks
providersNoList of provider names to query (optional, uses all if not specified)

Output Schema

NameRequiredDescriptionDefault
responsesYes

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. Changed5 schema fields changedv1.2.3
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / images
      Added value: +{
      +  "description": "Optional images to include with the prompt (for vision-capable models)",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "data": {
      +        "description": "Base64-encoded image data",
      +        "type": "string"
      +      },
      +      "mimeType": {
      +        "description": "MIME type (e.g., \"image/png\") — required for base64 data, optional for URLs",
      +        "type": "string"
      +      },
      +      "url": {
      +        "description": "Image URL — passed directly to the LLM provider",
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / providers / items / enum
      Added value: +[
      +  "openai",
      +  "google",
      +  "groq",
      +  "ollama"
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "responses": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "content": {
      +            "type": "string"
      +          },
      +          "error": {
      +            "type": "string"
      +          },
      +          "latency": {
      +            "type": "number"
      +          },
      +          "model": {
      +            "type": "string"
      +          },
      +          "nickname": {
      +            "type": "string"
      +          },
      +          "provider": {
      +            "type": "string"
      +          },
      +          "tokens": {
      +            "anyOf": [
      +              {
      +                "additionalProperties": false,
      +                "properties": {
      +                  "completion": {
      +                    "type": "number"
      +                  },
      +                  "prompt": {
      +                    "type": "number"
      +                  },
      +                  "total": {
      +                    "type": "number"
      +                  }
      +                },
      +                "required": [
      +                  "prompt",
      +                  "completion",
      +                  "total"
      +                ],
      +                "type": "object"
      +              },
      +              {
      +                "type": "null"
      +              }
      +            ]
      +          }
      +        },
      +        "required": [
      +          "provider",
      +          "nickname",
      +          "model",
      +          "content",
      +          "latency",
      +          "tokens"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "responses"
      +  ],
      +  "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, so the safety profile is covered. The description adds that queries are issued simultaneously across providers, which is genuinely useful behavioral context. It omits cost/latency implications of fanning out to multiple providers and does not clarify what a 'duck' is (a configured model endpoint) or what happens when a provider fails.

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 twelve-word sentence with the core behavior front-loaded and no filler. It is efficient, though the brevity borders on under-specification given the number of near-neighbor sibling tools.

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?

With an output schema present and full parameter documentation, the definition covers the mechanical requirements for a correct call. What is missing is the disambiguation layer: an agent choosing among ask_duck, compare_ducks, duck_council, duck_vote, duck_debate, and duck_judge gets no signal about which fan-out tool fits which intent. Cost/comparison semantics of a parallel multi-provider call are also unaddressed.

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 prompt, providers, model, and images thoroughly. The description only reinforces the 'same question to all ducks' framing and adds no detail about provider selection, the default-to-all behavior, or vision constraints beyond what the schema states. Baseline 3 applies when the schema does the heavy lifting.

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 concrete action (ask the same question) with an explicit scope qualifier (to multiple ducks simultaneously), which separates it from the single-target ask_duck and chat_with_duck. It does not, however, distinguish itself from siblings like duck_council, duck_vote, or duck_debate, which also fan out across multiple ducks.

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 guidance at all — nothing says when to pick this over ask_duck (single answer) or duck_council / duck_debate (multi-duck deliberation). The only cue is the implied intent of comparing responses, which the agent must infer from the word 'compare' in the name rather than from the description.

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