Skip to main content
Glama

SCRIPTMASTERLABS — Calibration Court

Model Calibration Leaderboard

court_leaderboard
Read-only

Live ranking of decision models by Brier score on resolved real-world questions. Free. Returns empty lists when nothing has resolved.

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": "court_leaderboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_typeNoOptional task category filter (a forecast domain, e.g. 'macro' or 'sports'); omit to rank models across all task types.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / task_type / description
      Added value: +"Optional task category filter (a forecast domain, e.g. 'macro' or 'sports'); omit to rank models across all task types."
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds genuinely new behavior: results are live, there is no cost, and empty lists are returned when nothing has resolved — a critical detail that prevents an agent from misreading an empty response as a failure. Auth and pagination behavior remain unstated.

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, front-loaded with what is ranked and how it is scored. 'Free.' is a fragment that still carries decision-relevant information, so little space is wasted, though the phrasing is slightly clipped.

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 read-only, zero-required-parameter ranking tool with no output schema, the description covers what is measured, freshness, cost, and the empty-result edge case. Only the shape of the returned ranking entries is left unstated, which is acceptable here.

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 the single optional 'task_type' parameter is fully documented in the schema, so the description correctly defers to it. The description adds no additional meaning such as default ranking semantics beyond what the schema already says.

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?

Names a specific resource (decision models) and metric (Brier score on resolved real-world questions), which is concrete enough for an agent to know what it returns. It does not explicitly contrast itself with 'court_model_report', so the sibling differentiation is left implicit.

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 — the word 'ranking' suggests comparing models rather than inspecting one, but there is no explicit 'use this when' or 'use court_model_report instead' guidance. The 'Free' note hints it is safe to call casually without stating so.

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