Prediction Markets Quant

Weather Settlement Tracker — what each venue settles at if nothing changes

weather_settlement

Read-only

Use for "what will the Kalshi NYC high settle at", "has LAX already hit 75" and "which Polymarket temperature bucket is winning". Per station: the running max under each venue's settlement rule (Kalshi and Polymarket US on the NWS Climate Report; Polymarket.com on routine METARs), the observation that set it, the next report countdown, the strikes already decided and the official high once it lands. Pass station ("la", "KLAX"). Settlement data only, no picks.

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": "weather_settlement"
  }
}

Input Schema

Name	Required	Description	Default
`station`	No	Station or city ("la", "KLAX", "nyc", "KXHIGHCHI", "LGA"). Omit for every tracked station.

Output Schema

Name	Required	Description
`as_of`	No	When the board was read.
`rules`	No	The three settlement rules (Kalshi, Polymarket US, Polymarket.com) in one sentence each.
`sources`	No
`stations`	No	Per station: the running max under each venue’s settlement rule, the observation that set it, the next report countdown, decided strikes/buckets, the official high once it lands.
`tell_user`	No	Show this sentence to the user first.
`timestamp`	No
`needs_input`	No
`example_call`	No
`data_freshness`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real substance beyond that: which data source each venue settles on (NWS Climate Report for Kalshi and Polymarket US, routine METARs for Polymarket.com) and that settlement is defined as 'if nothing changes'. It does not discuss update latency beyond the countdown or failure modes when a report is missing.

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 with the three trigger examples an agent most needs, then a dense enumeration of returned fields, then the scope caveat. The middle sentence is long and comma-heavy, but each clause carries distinct information and nothing is redundant.

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?

An output schema exists, so return values need no prose explanation, and the description still frames what the agent will see well enough to set expectations. The one gap is coverage of the station namespace for the omit case — it says 'every tracked station' without indicating scope or how stations are resolved.

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% and the sole parameter already documents accepted forms ('la', 'KLAX', 'nyc', 'KXHIGHCHI', 'LGA') plus the omit-for-all behavior. The description repeats those examples and the omission rule without adding format, casing, or resolution-order detail, so it lands at the baseline.

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?

Names a specific resource (per-station settlement values by venue) and enumerates exactly what is returned: running max under each venue's rule, the setting observation, next report countdown, decided strikes, official high. The closing line 'Settlement data only, no picks' draws a sharp boundary against the price/edge siblings.

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?

Three quoted trigger queries ('what will the Kalshi NYC high settle at', 'has LAX already hit 75', 'which Polymarket temperature bucket is winning') tell an agent precisely which user phrasings select this tool, and 'no picks' excludes analysis/edge tools. It stops short of naming a sibling to use instead when the user does want a trade recommendation.

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

All Prediction Markets Quant tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.