Skip to main content
Glama

SCRIPTMASTERLABS — Calibration Court

Recalibrate a Model Probability

court_recalibrate
Read-only

Paid (x402: USDC on Base, USDC on Solana, XRP on XRPL, USDC on Arc, or XAH on Xahau). Map a model's raw probability to an empirically calibrated one using resolved outcomes on the ledger. Refuses with insufficient_data below 30 samples.

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": {
      "model": "<model>",
      "prob": "<prob>"
    },
    "name": "court_recalibrate"
  }
}

Input Schema

NameRequiredDescriptionDefault
probYesThe model's raw predicted probability to recalibrate, between 0 and 1.
modelYesModel identifier whose resolved ledger predictions define the calibration mapping (e.g. 'jev-1.14.0'). The model needs at least 30 resolved predictions or the call refuses with insufficient_data.
task_typeNoOptional task category filter; omit to fit the mapping on all of the model's resolved predictions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / model / description
      Added value: +"Model identifier whose resolved ledger predictions define the calibration mapping (e.g. 'jev-1.14.0'). The model needs at least 30 resolved predictions or the call refuses with insufficient_data."
    • addedInput schema / properties / prob / description
      Added value: +"The model's raw predicted probability to recalibrate, between 0 and 1."
    • addedInput schema / properties / task_type / description
      Added value: +"Optional task category filter; omit to fit the mapping on all of the model's resolved predictions."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds substantially beyond that by disclosing that the call is paid via x402 with an enumerated set of accepted tokens/chains, and that it fails with a named insufficient_data error below 30 samples. It does not state the price, latency, or whether repeated calls re-fit the mapping.

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 compact sentences with no filler, but the payment preamble leads ahead of the actual purpose, so the core 'map a raw probability to a calibrated one' statement is not front-loaded. Minor structural deduction only.

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 three-parameter, read-only computation with no output schema, the definition covers the data source, the payment model, and the refusal condition — enough to call it correctly. It omits what the response contains (a calibrated probability and presumably supporting statistics), which the missing output schema makes slightly more costly.

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 model, prob, and task_type are already documented, including the 0–1 bound and the 30-sample requirement. The description adds no syntax, formatting, or edge-case meaning beyond what the schema already carries, so the baseline applies.

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?

States a specific verb and resource — mapping a model's raw probability to an empirically calibrated one — and names the data source (resolved outcomes on the ledger). An agent can distinguish this from court_calibrate_labels by the object being calibrated (probabilities vs labels) without opening either 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?

Gives a concrete precondition (at least 30 resolved samples, otherwise insufficient_data refusal), which is useful routing context, but never says when to prefer this over court_calibrate_labels or court_model_report. Usage is implied by the precondition rather than explicitly guided.

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