Skip to main content
Glama

SCRIPTMASTERLABS — Calibration Court

Calibrate Probabilities on Your Labelled Outcomes

court_calibrate_labels
Read-only

Paid (x402: USDC on Base, USDC on Solana, XRP on XRPL, USDC on Arc, or XAH on Xahau). Fit isotonic calibration on YOUR labelled outcomes ({p,y} pairs) and recalibrate the given probabilities. Stateless; nothing is stored.

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": {
      "examples": "<examples>",
      "probs": "<probs>"
    },
    "name": "court_calibrate_labels"
  }
}

Input Schema

NameRequiredDescriptionDefault
probsYesProbabilities to recalibrate with the fitted mapping, each between 0 and 1.
examplesYesYour labelled outcomes used to fit the isotonic calibration: objects with p (the probability you predicted, 0-1) and y (the realised outcome, 0 or 1).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / examples / description
      Added value: +"Your labelled outcomes used to fit the isotonic calibration: objects with p (the probability you predicted, 0-1) and y (the realised outcome, 0 or 1)."
    • addedInput schema / properties / examples / items / properties / p / description
      Added value: +"Predicted probability for this example, between 0 and 1."
    • addedInput schema / properties / examples / items / properties / y / description
      Added value: +"Realised outcome for this example: 1 if the event happened, 0 if it did not."
    • addedInput schema / properties / probs / description
      Added value: +"Probabilities to recalibrate with the fitted mapping, each between 0 and 1."
  2. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds genuinely useful undisclosed traits: the call is paid via x402 with enumerated payment rails, and it is stateless with nothing stored. It does not mention practical constraints that matter for isotonic fitting (minimum example count, tie handling, or what the returned values look like).

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?

Three short sentences with no filler. The one weakness is ordering: the payment/x402 sentence is front-loaded ahead of the statement of what the tool actually does, so the purpose arrives second.

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

Completeness3/5

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

For a two-parameter statistical tool with no output schema, the description should say something about the response (shape, alignment with input probs) and any minimum-data requirement for fitting isotonic regression. Payment and statelessness are well covered, but the return side is entirely absent.

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 both parameters are fully documented in the schema, including the p/y semantics of each example object. The description restates that examples are {p,y} pairs and that probs are recalibrated, adding no format, ordering, or constraint detail beyond the schema.

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: 'Fit isotonic calibration on YOUR labelled outcomes ... and recalibrate the given probabilities', which is clearly distinct from a generic recalibration sibling because it emphasizes user-supplied labels. It does not, however, explicitly contrast itself with court_recalibrate, leaving the agent to infer the difference.

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?

Usage is only implied ('YOUR labelled outcomes') – the agent can infer this is for users who bring their own {p,y} data, but there is no explicit when-to-use/when-not statement nor any routing to court_recalibrate for the pre-fitted case. No prerequisites or data-size requirements are given.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources