TopxAI Models

Judge with Jev

judge

Ask TypeSafe's Jev (a System One model) typed questions about a piece of text and get calibrated numbers back, not prose: a probability for a yes/no question (type noul), one option with a probability per option (type choice, with criteria), or a value on a scale with a probability per anchor (type score, with anchors). Billed at Jev's input-token price plus a $0.001 call fee.

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": {
      "state": "<state>",
      "questions": "<questions>"
    },
    "name": "judge"
  }
}

Input Schema

Name	Required	Description
`model`	No	System One model.
`state`	Yes	The text the questions are about: a ticket, a log excerpt, a document, a transcript.
`questions`	Yes	Question id to typed question. Each question is {"type": "noul" \| "choice" \| "score", "instructions": "one question a careful reader could answer from the state alone"}. noul may add "criteria": {"true": ..., "false": ...}; choice adds "criteria": {option: description or null, ...} (a plain list of option names is accepted too); score adds "criteria": [level description, ...] with 2 to 10 ordered levels.

Output Schema

Name	Required	Description
`error`	No	Present on a failed call: category (client, wallet, topxai, upstream, budget), message, charged, charged_usd.
`model`	No
`route`	No
`usage`	No
`answers`	No	Question id to answer: {type, noul} for a probability, {type, choice, confidence, probabilities} for a choice, {type, score, confidence, probabilities} for a score.
`charged`	No	Whether the wallet was debited for this call.
`request_id`	No	The relay request id; the same id appears in the usage log.
`charged_usd`	No	The recorded wallet debit in USD, model price and call fee included.
`call_fee_usd`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the shape of what comes back per question type and the billing model (input-token price plus a $0.001 call fee). Latency, failure modes, and permission/auth needs are not covered, which keeps it below a 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?

Effectively one front-loaded sentence with a colon-delimited enumeration of the three modes, then a short cost note. Every clause carries information; there is no filler or repetition.

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?

An output schema exists and parameter coverage is complete, so return values need no explanation here; cost, mode semantics, and input expectations are covered. The one gap is the 'model' parameter, which is left unexplained and unlinked to the list_models sibling that presumably enumerates valid values.

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 nested question structure, criteria formats, and level ranges are already documented in the schema. The description restates the three types and what each yields but adds no syntax or constraint detail beyond the schema, making 3 the correct baseline.

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 specific verb and resource: ask Jev typed questions about a piece of text and receive calibrated numbers rather than prose. The three output modes (noul/choice/score) sharpen what 'judge' means. It does not explicitly contrast with the sibling ask_model, so differentiation is implicit rather than stated.

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 phrase 'calibrated numbers back, not prose' implies when this is preferable to a prose-generating model call, but there is no explicit when-to-use/when-not or named alternative. Nothing tells the agent to use ask_model for open-ended generation or list_models to discover model names.

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

All TopxAI Models 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?