Skip to main content
Glama

model_probability

Read-only

Get a calibrated ML probability for one Kalshi or Polymarket market and compare it with the live market price using public API data, with no account needed.

Instructions

Get oracle3's calibrated machine-learning probability for one open market, next to its market price.

The model was trained on resolved Kalshi and Polymarket contracts using only
information available at prediction time: the displayed price, time to the
scheduled end, recent price changes and volatility, spread and traded volume
(Kalshi), and category. It was tuned with event-grouped, purged walk-forward
cross-validation and recalibrated with isotonic regression on training folds.
The features are rebuilt from the venue's public API at call time, so no
account is needed. Returns model_probability, market_price, their difference,
the model's out-of-sample scores against market prices and the features used.
It is an estimate, not a trading signal; read the rules with get_market.
Requires the ML extra: pip install 'oracle3[ml]'.

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": {
      "venue": "<venue>",
      "market_id": "<market_id>"
    },
    "name": "model_probability"
  }
}

Input Schema

NameRequiredDescriptionDefault
venueYesVenue: 'kalshi' or 'polymarket'.
market_idYesKalshi market ticker (e.g. KXFEDDECISION-28JAN-H0) or Polymarket market id (e.g. 2589812), as returned by search_markets.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.3.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly and openWorld, so safety is covered. The description adds genuinely non-obvious behavior: features are rebuilt from the venue's public API at call time, no authentication is required, an optional ML dependency must be installed or the call will fail, and the result is an estimate rather than a signal. The training-methodology sentences (walk-forward CV, isotonic recalibration) add credibility but less operational value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, which is good, but a large share of the text is model-training detail (event-grouped purged walk-forward CV, isotonic regression) that an agent cannot act on. The actionable facts, the ML-extra prerequisite and the get_market pointer, are buried in the middle and final sentence.

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?

With an output schema present, return values need not be spelled out, yet the description still summarizes them (probability, price, difference, scores, features). For a tool with a non-default dependency and a notable caveat, the definition covers the prerequisites, the lack of auth, and the interpretation limits. A slightly tighter ordering would make it complete at a 5.

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 carry their own descriptions with an example ticker/id format and a pointer to search_markets, so the schema does the heavy lifting. The description adds no parameter-level meaning beyond noting the market must be open. Baseline 3 is appropriate.

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 concrete verb and resource: 'Get oracle3's calibrated machine-learning probability for one open market, next to its market price.' Scope ('one open market') and output semantics (probability vs. price) are explicit, letting an agent tell this apart from a generic pricing tool. It does not name a sibling alternative (e.g. fair_value) to sharpen the contrast, which keeps it short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for use: it operates on an open market, needs no account, and the agent is told to 'read the rules with get_market' before acting, plus a hard prerequisite (pip install 'oracle3[ml]'). It also cautions that the output 'is an estimate, not a trading signal.' There is no explicit when-not or named alternative for pure market pricing, so 4 rather than 5.

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