Skip to main content
Glama
Sign In
Firnschnee

Dual Model MCP Server

by Firnschnee
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Multi-Modell-Anfrage

query_dual_models

Sends one prompt to multiple AI models in parallel via OpenRouter and returns each answer side by side, with optional synthesis of convergences and contradictions for hard problems.

Instructions

Schickt eine Prompt parallel an mehrere Modelle via OpenRouter (Standard: anthropic/claude-fable-5.1, openai/gpt-6-astra, Reasoning-Effort high). Eskalationsstufe für harte Probleme, nicht für Routinefragen: teuer und langsam. Liefert alle Antworten nebeneinander, optional mit Synthese (Konvergenzen, Widersprüche, Unikate). Standard-System-Prompt: strukturierte Antwort in 6-8 Absätzen.

Input Schema

NameRequiredDescriptionDefault
effortNoOptional: Reasoning-Effort für alle Modelle. Standard: high
modelsNoOptional: OpenRouter-Modell-IDs für diesen Aufruf. Standard: anthropic/claude-fable-5.1, openai/gpt-6-astra
promptYesDie Prompt für alle Modelle
max_tokensNoOptional: max_tokens pro Modell. Standard: 32000
synthesizeNoOptional: Zusätzlicher Vergleichsschritt über alle Antworten (Konvergenzen, Widersprüche, Unikate).
temperatureNoOptional: Temperature. Standard: nicht gesetzt (Provider-Default). Reasoning-Modelle von OpenAI und Anthropic ignorieren den Parameter.
system_promptNoOptional: Custom System-Prompt. Falls leer: Standard-Prompt (strukturiert, 6-8 Absätze).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.2.2
    • addedInput schema / properties / effort
      Added value: +{
+  "description": "Optional: Reasoning-Effort für alle Modelle. Standard: high",
+  "enum": [
+    "none",
+    "minimal",
+    "low",
+    "medium",
+    "high",
+    "xhigh",
+    "max"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / max_tokens / description
      Previous value: -"Optional: max_tokens pro Modell. Standard: 6000"New value: +"Optional: max_tokens pro Modell. Standard: 32000"
    • changedInput schema / properties / models / description
      Previous value: -"Optional: OpenRouter-Modell-IDs für diesen Aufruf. Standard: anthropic/claude-opus-4.8, openai/gpt-5.5"New value: +"Optional: OpenRouter-Modell-IDs für diesen Aufruf. Standard: anthropic/claude-fable-5.1, openai/gpt-6-astra"
    • changedInput schema / properties / temperature / description
      Previous value: -"Optional: Temperature. Standard: 0.7"New value: +"Optional: Temperature. Standard: nicht gesetzt (Provider-Default). Reasoning-Modelle von OpenAI und Anthropic ignorieren den Parameter."
  2. Changed8 schema fields changedv1.0.1
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / max_tokens
      Added value: +{
+  "description": "Optional: max_tokens pro Modell. Standard: 6000",
+  "exclusiveMinimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / models
      Added value: +{
+  "description": "Optional: OpenRouter-Modell-IDs für diesen Aufruf. Standard: anthropic/claude-opus-4.8, openai/gpt-5.5",
+  "items": {
+    "type": "string"
+  },
+  "minItems": 1,
+  "type": "array"
+}
    • changedInput schema / properties / prompt / description
      Previous value: -"Die Prompt für beide Modelle"New value: +"Die Prompt für alle Modelle"
    • addedInput schema / properties / synthesize
      Added value: +{
+  "description": "Optional: Zusätzlicher Vergleichsschritt über alle Antworten (Konvergenzen, Widersprüche, Unikate).",
+  "type": "boolean"
+}
    • changedInput schema / properties / system_prompt / description
      Previous value: -"Optional: Custom System-Prompt. Falls leer: Standard-Prompt (strukturiert, prägnant, 6-8 Absätze)."New value: +"Optional: Custom System-Prompt. Falls leer: Standard-Prompt (strukturiert, 6-8 Absätze)."
    • addedInput schema / properties / temperature
      Added value: +{
+  "description": "Optional: Temperature. Standard: 0.7",
+  "maximum": 2,
+  "minimum": 0,
+  "type": "number"
+}
  3. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations the description carries the whole burden, and it delivers: cost/latency warning, default model set, default effort, default system prompt, and the return shape (all answers side by side, optional synthesis). It omits rate limits, auth requirements, and per-model failure behavior, keeping it short of 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, all front-loaded: purpose first, then usage gating with the cost caveat, then output and default behavior. No filler and nothing buried.

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?

For a 7-parameter tool with no output schema and no annotations, the description covers purpose, cost, defaults, and return shape well. Minor gaps remain around error handling and what happens when individual models fail, but the essentials for correct invocation are present.

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 is already documented in the schema, including defaults for effort, models, max_tokens and system_prompt. The description mostly repeats those defaults rather than adding format or constraint meaning, so the baseline 3 applies.

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 (schickt ... parallel an mehrere Modelle) and resource (multi-model query via OpenRouter), and the multi-model scope directly distinguishes it from the single-model sibling ask_gpt. An agent can tell them apart immediately.

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?

Explicitly frames when to use it (Eskalationsstufe für harte Probleme) and when not (nicht für Routinefragen), with the cost/latency rationale. It does not name ask_gpt as the concrete alternative for routine single-model queries, so it falls short of full 5.

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