argon-bridge-9router

Overview Schema Source Related Servers Discussions Admin

ask_argon_playwright_9router

Routes coding, architecture, and debugging prompts to Gemini 4 Argon through a Playwright browser session, falling back to 9Router models when the browser is unavailable.

Instructions

Execute coding, architecture, or debugging prompts via Gemini 4 Argon (Playwright Web Bridge) or any 9Router provider/model (including Qoder, Antigravity Claude Opus/Sonnet 4.6, Qwen, DeepSeek, or custom Smart Combos).

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": "ask_argon_playwright_9router"
  }
}

Input Schema

Name	Required	Description
`mode`	No	'playwright-first' tries Gemini 4 Argon via browser first then falls back to 9Router. '9router-combo-first' skips Playwright and calls the 9Router fallback chain directly. 'custom-model' routes directly to the model specified in target_model.
`prompt`	Yes	The coding instruction, architectural question, or debugging prompt.
`target_model`	No	Optional: Specific 9Router model ID or combo to target (e.g., 'qoder/qwen3-coder-plus', 'ag/claude-sonnet-4-6-thinking', 'jio-max-non-gemini'). Used first before fallback chain.
`system_prompt`	No	Optional system instruction.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Nov 4, 2026

TDQS

B3.1/5.0

Behavior2/5

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

No annotations are provided, so the description must carry the full behavioral burden, but it does not. It says nothing about fallback behavior when Playwright fails, expected latency of the browser bridge, authentication or credential requirements for the third-party providers, rate limits, or whether the tool has side effects beyond returning text.

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?

One front-loaded sentence with the action and backends stated first, followed by the provider list. It is efficient, though the long parenthetical list of model names is somewhat dense and could be trimmed.

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

Completeness2/5

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

For a tool that drives a browser session and routes across multiple external providers, the definition is thin: no output schema exists, and the description does not describe what a response looks like or how failures and fallbacks surface. The schema compensates on parameters but not on overall behavior.

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 coverage is 100%, so mode, prompt, target_model, and system_prompt are already documented, including the mode enum semantics. The description adds marginal value by naming concrete provider/model families (Qoder, Antigravity Claude Opus/Sonnet 4.6, Qwen, DeepSeek, Smart Combos) that clarify what target_model can accept, but it does not explain mode interplay beyond what the schema states.

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 verb ("Execute") and names the resource types (coding, architecture, or debugging prompts) plus the two execution backends, Gemini 4 Argon via Playwright and any 9Router provider/model. The purpose is clear, though the description does not explain how the three routing modes differ; that detail is only in the schema.

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?

The prompt categories (coding, architecture, debugging) imply when the tool is appropriate, and the provider list hints at the routing choice. However, there is no explicit when-to-use or when-not-to-use guidance, no mention of when to prefer Playwright versus the 9Router chain, and no prerequisites. With no sibling tools, the missing routing guidance is the main gap.

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

ask_argon_playwright_9routerB