Kingy AI Facts

Find models that fit a budget or need

find_models_that_fit

Read-onlyIdempotent

Filter currently priced models by maximum input or output price (USD per 1M tokens), minimum context window, minimum output tokens, provider, or a Kingy home-hardware verdict, sorted by price or context. Facts only: it does not rank quality.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_models_that_fit"
  }
}

Input Schema

Name	Required	Description
`sort`	No	Default cheapest_input.
`limit`	No	Default 10.
`provider`	No	Only this provider.
`must_run_on`	No	Only models with a Kingy "Yes" or "Yes, but slow" verdict for this machine type.
`min_output_tokens`	No	Smallest acceptable maximum output per request.
`min_context_window`	No	Smallest acceptable context window in tokens.
`max_input_usd_per_1m`	No	Highest acceptable input price.
`max_output_usd_per_1m`	No	Highest acceptable output price.
`include_automated_parse`	No	Include extended providers parsed automatically. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedInput schema / properties / must_run_on / enum

Previous value: -[
-  "laptop-16gb",
-  "gpu-24gb",
-  "gpu-32gb",
-  "mac-64gb",
-  "unified-128gb",
-  "mac-512gb"
-]New value: +[
+  "gpu-8gb",
+  "laptop-16gb",
+  "mac-24gb",
+  "gpu-24gb",
+  "gpu-32gb",
+  "mac-64gb",
+  "unified-128gb",
+  "mac-512gb"
+]

AddedNov 6, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare this as a read-only, idempotent, closed-world query, so the description only needed to add scope. It does so usefully by stating that only "currently priced models" are considered and that results are unranked facts, which prevents the agent from misreading output as a quality ordering.

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?

Two dense sentences with the filter surface front-loaded and the caveat last; every clause maps to a real parameter or a real behavioral constraint, with no filler.

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 nine-parameter, all-optional, read-only filter tool with full schema coverage and no output schema, the description covers the filtering model and result ordering adequately. It stops short of describing result shape or the effective default limit behavior, but no output contract exists to require it.

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% and every parameter including enums and defaults is documented in the schema, so this is the baseline case. The description adds only light framing, mapping the filters to their units (USD per 1M tokens) and clarifying that the hardware filter is a Kingy verdict, without extending beyond the schema.

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 opens with a specific verb and resource ("Filter currently priced models") and enumerates the exact filter axes and sort options, so an agent can immediately tell this is a price/context filtering tool rather than a lookup or search tool like get_model_prices or search_kingy.

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 final clause, "Facts only: it does not rank quality," acts as a boundary on when not to rely on it, and the filter list implies the use case. However, no sibling tool is named and no explicit condition (e.g., 'use get_model_prices for the full table') routes the agent between alternatives.

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

All Kingy AI Facts tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?