Skip to main content
Glama
Sign In
playcal

playcal

by RizgarOzan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

playcal_calibrate

Predict each level's human pass rate from bot runs, calibrate it on a small human panel with 95% intervals, and flag levels that fall outside target bands.

Instructions

predict each level's human pass rate from bot runs, calibrated on a small human panel, with 95% intervals

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": "playcal_calibrate"
  }
}

Input Schema

NameRequiredDescriptionDefault
botNoevent JSONL from bot runs, same schema
humanNoevent JSONL from the human panel (accepted.jsonl from ingest)
targetsNoJSON {"4": [40, 60]}: predicted human pass-rate band per level; a level outside its band exits 1
min_attemptsNohuman attempts a level needs to count for calibration (default 5)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the statistical method and interval width, which is genuinely useful, but says nothing about side effects (does it write files or print to stdout?), what the output looks like, runtime cost, or the exit-1 band-check behavior that the schema mentions only for one parameter.

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?

A single front-loaded sentence with the verb first and no filler. It is dense and efficient, though the compactness means several operational details are simply absent rather than compressed.

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?

With four parameters, no annotations, and no output schema, the description should explain what the tool returns (a prediction table? JSON? file path?) and how the two input streams are supplied. The required list is empty despite array inputs, and the description does not clarify this or the result format, leaving a real gap for an agent.

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 all four parameters are documented in the schema, including formats, the default of 5, and the exit-1 band failure. The description adds only high-level framing ('bot runs', 'small human panel') and no format or constraint detail beyond the schema, so baseline 3 applies.

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: 'predict each level's human pass rate from bot runs', plus the calibration method and interval width. It is not explicitly contrasted with siblings like playcal_report or playcal_baseline, but the statistical-prediction framing is distinctive enough that an agent can differentiate it.

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 strongly implied: use this when you have bot-run JSONL and human-panel JSONL and want per-level pass-rate predictions with intervals. There is no explicit when-not guidance, no mention of prerequisites (e.g., that ingest must run first for accepted.jsonl), and no named alternative.

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

Deploy Server

Other Tools