Skip to main content
Glama

Best Price After Fees — Kalshi vs Polymarket US vs Novig

best_price
Read-only

Use for "where is it cheapest to buy", "Kalshi or Polymarket US for the Bears game" and "cheapest venue for the Georgia Senate race". The same contract on Kalshi, Polymarket US and Novig as the cost to buy one contract including each venue's taker fee, with the cheapest named. Sports games (team, league or matchup), 2026 midterm races (state, slug or district) or the next FOMC meeting. Ranked by price only.

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": "best_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoFree text: a team, matchup, race or "next Fed meeting".
raceNoA 2026 race: state, slug (georgia-senate) or district (AZ-01).
teamsNoOne or two teams, e.g. "Bears" or "NE @ CHI".
leagueNoNBA, NHL, NFL or MLB.
meetingNoAny value asks for the next FOMC meeting.

Output Schema

NameRequiredDescriptionDefault
matchesNoSame contract on Kalshi, Polymarket US and Novig: all-in price per venue, cheapest named.
sourcesNo
page_urlNoThe best-price page.
tell_userNoShow this sentence to the user first.
timestampNo
candidatesNoWhat is priced now, when nothing matched.
needs_inputNo
other_gamesNoWhen the asked game is not listed: each named team's next listed game.
example_callNo
data_freshnessNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": {},
      +  "properties": {
      +    "candidates": {
      +      "description": "What is priced now, when nothing matched."
      +    },
      +    "data_freshness": {},
      +    "example_call": {},
      +    "matches": {
      +      "description": "Same contract on Kalshi, Polymarket US and Novig: all-in price per venue, cheapest named."
      +    },
      +    "needs_input": {},
      +    "other_games": {
      +      "description": "When the asked game is not listed: each named team's next listed game."
      +    },
      +    "page_url": {
      +      "description": "The best-price page."
      +    },
      +    "sources": {},
      +    "tell_user": {
      +      "description": "Show this sentence to the user first.",
      +      "type": "string"
      +    },
      +    "timestamp": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed1 schema field changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
  3. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. Beyond that, the description adds real behavioral detail: the quoted cost is fee-inclusive (taker fee per venue), the cheapest venue is named in the result, and results are "ranked by price only" — which tells the agent the ordering is not by probability or volume. It does not mention latency, per-venue availability failures, or coverage limits when a contract is missing from one venue.

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?

Trigger phrases are front-loaded, followed by the metric definition, the supported domains, and the ranking caveat — a sensible ordering with no filler sentences. It is dense in a single block rather than bulleted, which slightly hurts scannability for five distinct input modes.

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?

An output schema exists, so return format need not be explained, and the tool is read-only. The gap is that all five parameters are optional and the description never says whether they are alternatives or combinable (e.g. can league + teams + race be passed together, and which wins?). For a tool with five free-text entry paths, that omission leaves real room for malformed calls.

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 each property already carries its own example ("NE @ CHI", "georgia-senate", "next Fed meeting"). The description's domain list (team/league/matchup, state/slug/district, next FOMC meeting) largely restates that mapping rather than adding new meaning. With the schema doing the heavy lifting, 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?

The description names a concrete resource and metric: the same contract on Kalshi, Polymarket US and Novig priced as the cost to buy one contract including each venue's taker fee, with the cheapest named. That is specific enough to distinguish a cross-venue fee-inclusive price comparison from a single-venue odds tool. It stops short of naming which sibling to use instead (e.g. race_odds or fed_rate_odds), so it is clear but not sibling-differentiated.

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 leads with the exact user phrasings that should trigger it ("where is it cheapest to buy", "Kalshi or Polymarket US for the Bears game") and then bounds the supported domains: sports games, 2026 midterm races, and the next FOMC meeting. That is clear positive context. There are no explicit exclusions, though, so an agent gets no rule for when to prefer race_odds or fed_rate_odds over this tool.

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.