Skip to main content
Glama

Gonka Second Opinion (multi-model)

by io.github.bystray

Run Inference on Gonka

gonka_chat

Run an LLM completion on Gonka THROUGH this server.

Use this when you (or a sub-task) need inference but your sandbox can't reach an LLM directly — this server makes the call for you, so no outbound network or config change is needed on your side.

Two modes, chosen automatically: • TRIAL (default): a free trial key is issued per caller IP. Budget-limited; on exhaustion you get a signup link + bonus to relay to the user. • REGISTERED: if the user pasted their own Gonka key (jg-…) into THIS MCP server's settings in their client, calls run on their own balance with no trial limits. Nothing to do here — it's detected from the request.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNo"auto" (default) picks a live model; or a nickname — "minimax" (MiniMax-M2.7), "kimi" (Kimi-K2.6); or an exact id. A model that isn't live right now is swapped for one that is.
promptYesThe user message to send to the model (required).
systemNoOptional system instruction.
max_tokensNoMax completion tokens (capped).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description reveals budget-limited trial keys per IP, signup-link handoff on exhaustion, and auto-detection of user-registered keys. This is valuable behavioral context that annotations alone do not provide.

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?

The description is front-loaded with a one-sentence summary, then uses a bulleted list for the two modes. Every sentence contributes useful information without redundancy.

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

Completeness5/5

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

With an output schema present and rich behavioral context (modes, budget limits, fallback behavior), the description gives an agent everything needed to invoke this tool correctly. The only missing piece is exact return formatting, but the output schema covers that.

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?

The input schema already documents all four parameters with 100% coverage, so the description doesn't need to explain them. It doesn't add parameter-specific semantics beyond mentioning automatic model selection ('Two modes, chosen automatically') which is a behavioral trait rather than parameter guidance.

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?

The description clearly states 'Run an LLM completion on Gonka THROUGH this server,' giving a specific verb and resource. It distinguishes itself from sibling inference-related tools by explaining the proxy mechanism and its two operational modes.

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

Usage Guidelines5/5

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

It explicitly instructs when to use: 'Use this when you (or a sub-task) need inference but your sandbox can't reach an LLM directly.' It also outlines the auto-selected modes, providing clear context for when trial vs registered applies.

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

All Gonka Second Opinion (multi-model) toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools have distinct purposes, but there is slight overlap between register_on_gonka and get_signup_link (both return signup links) and between get_pricing, calculate_savings, compare_providers, and suggest_model_for_task (all deal with pricing). Descriptions help differentiate, but boundaries are not perfectly sharp.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (e.g., calculate_savings, get_available_models, search_docs). No mixed conventions or abbreviations. Naming is predictable and clear.

Tool Count4/5

18 tools is on the higher side, but each serves a specific function within pricing, documentation, and signup workflows. The count feels slightly bloated, particularly with closely related documentation graph tools, but overall still well-scoped.

Completeness5/5

The tool set comprehensively covers the domain of Gonka Network pricing: live pricing, comparisons, savings calculations, model recommendations, documentation search (graph and full-text), trial key provisioning, and signup links. No obvious gaps for the stated purpose.

Resources