Skip to main content
Glama

NS Pros MCP Gateway

noirlab-datalab__polymarket_kalshi_spread

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ, when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) topic, 11 pre-mapped macro subjects ("fed", "btc", "eth", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue.

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": {
      "topic": "fed"
    },
    "name": "noirlab-datalab__polymarket_kalshi_spread"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicNoSubject to compare. Canonical keys: fed | btc | eth | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president, plus the 15-minute crypto up/down windows btc_15m | eth_15m | sol_15m | xrp_15m | bnb_15m ("btc 15m", "bitcoin 15 minute"), which are answered by updown_venue_compare for the window in progress, but aliases and keywords resolve too ("bitcoin", "fed rate decision", "ethereum", "inflation", "s&p 500", "us recession", "next pope", "2028 election"). Check resolution.topic_matched_by in the response: "exact"/"alias" is a curated pairing, "phrase"/"token" is a keyword guess.
kalshi_event_tickerNoExplicit Kalshi event ticker, e.g. "KXFED-26OCT". Overrides the topic-mapped Kalshi side.
polymarket_event_slugNoExplicit Polymarket event slug, e.g. "fed-decision-in-june-825". Overrides the topic-mapped Polymarket side.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does disclose real behavior: the tool reports non-equivalent bet shapes rather than silently returning a bogus delta, and it exposes resolution.topic_matched_by so the agent can tell a curated pairing from a keyword guess. It does not cover auth requirements, rate limits, or what a full response contains, which keeps it below a 5.

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 opening framing is well front-loaded and earns its words, but the description terminates mid-enumeration after announcing "TWO MODES" and describing only mode 1. A dangling structural promise is worse than no enumeration at all, since the agent is primed to look for a mode-2 path that is never explained.

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 no output schema and three parameters, the description should explain what comes back and how the two modes relate. It partially compensates by referencing resolution.topic_matched_by and the shape-equivalence verdict, but the truncated mode list and absent return-shape description leave real gaps for a tool whose core value is a numeric delta plus a validity judgment.

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 canonical key list, alias resolution, and override precedence are already documented in the parameter descriptions and the description largely restates them. It adds some interpretive value by explaining that "exact"/"alias" means a curated pairing versus a "phrase"/"token" guess, but per the 100%-coverage baseline this sits at 3.

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?

The description names a specific verb and resource — cross-venue spread between Kalshi and Polymarket for the same resolving question — and explains the economic origin of that spread (differing participant pools, 2-25pp). An agent can distinguish this from the sibling edge/arbitrage tools without inspecting any schema.

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?

It gives concrete entry criteria: 11 pre-mapped topic keys with example aliases, plus explicit ticker/slug override parameters for when the curated mapping is wrong. It also routes the 15-minute crypto windows to updown_venue_compare for the in-progress window. The gap is the dangling "TWO MODES" header — mode 2 is never described, so the routing between topic mode and explicit-ticker mode must be inferred from the schema.

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.