Skip to main content
Glama

Kalshi Weather Edge

kalshi_weather_edge
Read-onlyIdempotent

Prices Kalshi daily high-temperature markets against the NWS forecast for the market's OWN settlement station, and measures whether that forecast actually beats the market. Two modes. LIVE (default): returns the full strike ladder for one city and settlement date with market_prob (mid), forecast_prob, and edge_pp per strike, plus the settlement clause verbatim. BACKTEST (backtest_days: N): scores an archived gridded forecast against the market on settled days and returns brier_market vs brier_forecast with a plain-English verdict, so the edge is MEASURED rather than asserted. READ THE WARNINGS, they are not boilerplate. (1) These markets DO NOT settle on the NWS. They settle on The Weather Company (weather.com) at a Kalshi station code such as CLINYC, which the response quotes verbatim; so part of every edge_pp is NWS-vs-Weather-Company disagreement about the same day at the same station, which is not mispricing and not tradeable. settlement_vs_forecast_basis_f from backtest mode is that part as a number. (2) The station is DERIVED from the settlement clause, never from the city name: Chicago settles at MIDWAY and New York at CENTRAL PARK, so a city-centre forecast would misprice a whole ladder. A station that cannot be resolved yields rows with no forecast and a reason, never a guessed coordinate. (3) forecast_prob assumes a normal distribution around the NWS high whose width is ASSUMED, not fitted (stated in distribution_assumption), run backtest mode to see whether it is calibrated. (4) edge_pp is gross: no Kalshi fees, no bid-ask. MEASURED RESULT, AND IT IS NOT THE FLATTERING ONE: on the first backtest (KXHIGHNY, 13 settled days to 2026-09-11, 58 market observations) the MARKET beat the forecast, Brier 0.1008 for the market against 0.1594 for the archived gridded forecast, lower being better. So on that sample there is NO forecast edge to sell, and a large edge_pp is more likely to be the model disagreeing with a better-informed market than an opportunity. The measured settlement-vs-forecast basis was 1.7F mean absolute over 8 pinnable days, slightly warm-biased, which is a big share of a typical edge_pp on a 2-degree bracket. Re-run backtest_days before believing any edge; if a later sample reverses this, the numbers say so. NWS is US-only, so the ~30 international Kalshi weather series (London, Paris, Tokyo) return market prices with forecast_unavailable rather than a forecast. Precipitation series are listed but not yet priced. Cities: nyc, chicago, los angeles, miami, austin, houston, denver, philadelphia, or pass series_ticker for any other (e.g. "KXHIGHTBOS").

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "city": "nyc"
    },
    "name": "kalshi_weather_edge"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity to price, e.g. "nyc", "chicago", "los angeles", "miami", "austin", "houston", "denver", "philadelphia". Defaults to nyc. Unmapped cities return known_cities[] rather than a wrong series.
dateNoSettlement date as YYYY-MM-DD. Defaults to the soonest open event. Daily weather markets open ~1-2 days ahead and close 05:00Z the next day.
market_typeNo"high_temp" (default) | "precip". Precipitation markets return prices but no forecast_prob yet.
backtest_daysNoRun measurement mode over the last N settled days (max 60) instead of pricing today. Returns brier_market vs brier_forecast, the settlement-vs-forecast basis, and per-day detail. Both sides are scored at 12:00Z on each event day, before the daily high and before resolution, because a settled market prices the known outcome at close.
series_tickerNoExplicit Kalshi series, e.g. "KXHIGHNY" or "KXHIGHTBOS" (Boston). Overrides `city`; use it for any of the 121 daily weather series not in the city list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / backtest_days / description
      Previous value: -"Run measurement mode over the last N settled days (max 60) instead of pricing today. Returns brier_market vs brier_forecast, the settlement-vs-forecast basis, and per-day detail. Both sides are scored at 12:00Z on each event day — before the daily high and before resolution — because a settled market prices the known outcome at close."New value: +"Run measurement mode over the last N settled days (max 60) instead of pricing today. Returns brier_market vs brier_forecast, the settlement-vs-forecast basis, and per-day detail. Both sides are scored at 12:00Z on each event day, before the daily high and before resolution, because a settled market prices the known outcome at close."
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark it read-only, idempotent, and non-destructive, but the description adds substantial undisclosed-by-schema behavior: edge_pp is gross of fees and bid-ask, forecast_prob uses an assumed (not fitted) normal width, the station is derived from the settlement clause rather than the city name, and unresolved stations return a reason instead of a guessed coordinate. The cited backtest result (market Brier 0.1008 vs forecast 0.1594) actively warns the agent that a large edge is more likely model-vs-market disagreement than opportunity.

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?

Front-loaded correctly: purpose, then the two modes, then the numbered warnings, then the measured result and coverage limits. Every warning carries real decision-relevant content, but the measured-result paragraph repeats numbers already implied by the backtest guidance and pushes overall length past what a caller needs before invoking.

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

Completeness5/5

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

There is no output schema, yet the description names the return fields (market_prob, forecast_prob, edge_pp, settlement clause verbatim, brier_market vs brier_forecast, verdict, distribution_assumption, settlement_vs_forecast_basis_f). All parameters are optional and their defaults are covered, so an agent has everything needed to call it and interpret the result.

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 the schema already documents all five parameters, and the description largely restates them (city list, series_ticker examples, backtest_days). It adds marginal meaning by stating series_ticker overrides city and covers ~121 daily weather series, but that is already present in the schema wording. Baseline 3 is appropriate.

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: prices Kalshi daily high-temperature markets against the NWS forecast for the market's own settlement station, and measures whether the forecast beats the market. The two-mode split (LIVE vs BACKTEST) and the explicit contrast with market-implied probabilities make it clearly distinct from the Polymarket siblings.

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

Usage Guidelines5/5

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

Explicitly says LIVE is the default, BACKTEST is selected by `backtest_days: N`, and that backtest should be re-run before believing any edge. It also names the conditions where the tool degrades (international series return forecast_unavailable, precipitation is listed but not priced) rather than leaving them to be discovered.

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.