Skip to main content
Glama

Prediction Markets Quant

by com.predictionmarketspicks
OverviewDiscussionsAdmin

Combo Edge Verdict

combo_edge
Read-only

Grade a same-game combo (parlay-style multi-leg position) on a prediction market against its fair value. Given each leg price in cents and your correlation-aware estimate of the true joint win probability, returns the fair-value ODDS BAND to grade a quote against. Pass offeredOdds — the price your platform actually quotes for the combo (Kalshi combo RFQ or an SGP product) — to get the expected-value %, a negative-correlation-trap flag, and a 7-tier verdict (SMASH / PLAY / LEAN / RISK / NO_VALUE / PASS / RUN). Without offeredOdds it returns fair value + band only (no verdict) — never grade EV off the product of the leg prices, which no venue pays. Use for "is this combo worth it", "grade my parlay quote", "same-game combo value". OR pass nflGame (AWAY-HOME — abbrevs, nicknames or full names all work: "NYG-LAR", "Giants vs Rams"; a reversed pair is read correctly) and we do the hard part for you: that game's real Kalshi legs, moneyline, spreads, the game-total ladder and PLAYER PROPS, both sides of every contract. Call it with nflGame alone to list the legs and their ids, then again with legIds to have us compute the correlation-aware joint ourselves — no estimate needed from you. Game legs are priced against a market-anchored fair line (edge = fair − market; the raw model is shown beside it). A prop is priced conditional on the game script — pace (the total) and flow (the margin) — inside the same model as the game legs, so four unders that all need a low-scoring game are priced as the correlated slip they are instead of being multiplied. From the PredictionMarketsPicks desk, which publishes a settled per-engine record — every signal graded against the market that priced it, wins and losses both: predictionmarketspicks.com/track-record.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
legIdsNo2–6 leg ids from a previous nflGame call. We compute the correlation-aware joint for exactly these legs.
nflGameNoAn NFL game on the live board, as "AWAY-HOME" (e.g. "NYG-LAR"). Alone: lists that game's selectable legs with their ids. With legIds: prices that exact combo.
legPricesNoEach leg's YES price in cents (1–99). Used only for the theoretical assemble ceiling. Omit when using nflGame + legIds — we read the real prices.
offeredOddsNoThe combo price your platform actually quotes — American odds (e.g. -150, 988) or a decimal payout multiplier (e.g. 10.7). Grades EV + verdict against fair value. Omit to get fair value + band only.
offeredAmericanNoAlias for offeredOdds (the response reports the quote as offered_american, so this name is accepted on input too). American odds or a decimal multiplier, same parsing. If both are given, offeredOdds wins.
trueWinProbabilityNoYour correlation-aware estimate of the true joint probability all legs hit, in % (0–100). Omit when using nflGame + legIds — we compute it from the scoreline model.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / nflGame / description
      Previous value: -"An NFL game on the live board, as \"AWAY-HOME\" (e.g. \"NE-SEA\"). Alone: lists that game's selectable legs with their ids. With legIds: prices that exact combo."New value: +"An NFL game on the live board, as \"AWAY-HOME\" (e.g. \"NYG-LAR\"). Alone: lists that game's selectable legs with their ids. With legIds: prices that exact combo."
  2. Changed1 schema field changed
    • addedInput schema / properties / offeredAmerican
      Added value: +{
+  "description": "Alias for offeredOdds (the response reports the quote as offered_american, so this name is accepted on input too). American odds or a decimal multiplier, same parsing. If both are given, offeredOdds wins.",
+  "type": "number"
+}
  3. Changed5 schema fields changed
    • addedInput schema / properties / legIds
      Added value: +{
+  "description": "2–6 leg ids from a previous nflGame call. We compute the correlation-aware joint for exactly these legs.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 6,
+  "minItems": 2,
+  "type": "array"
+}
    • changedInput schema / properties / legPrices / description
      Previous value: -"Each leg's YES price in cents (1–99). Used only for the theoretical assemble ceiling."New value: +"Each leg's YES price in cents (1–99). Used only for the theoretical assemble ceiling. Omit when using nflGame + legIds — we read the real prices."
    • addedInput schema / properties / nflGame
      Added value: +{
+  "description": "An NFL game on the live board, as \"AWAY-HOME\" (e.g. \"NE-SEA\"). Alone: lists that game's selectable legs with their ids. With legIds: prices that exact combo.",
+  "type": "string"
+}
    • changedInput schema / properties / trueWinProbability / description
      Previous value: -"Your correlation-aware estimate of the true joint probability all legs hit, in % (0–100)."New value: +"Your correlation-aware estimate of the true joint probability all legs hit, in % (0–100). Omit when using nflGame + legIds — we compute it from the scoreline model."
    • removedInput schema / required
      Removed value: -[
-  "legPrices",
-  "trueWinProbability"
-]
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already indicate readOnlyHint=true, and the description adds rich behavioral context beyond that: output conditionality on offeredOdds, the edge formula (fair − market), how props are priced conditional on game script, the correlation-aware joint handling, and the legIds round-trip workflow. There is no contradiction with the read-only annotation.

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?

The description is long but justifiably so for a two-mode tool with six parameters. It front-loads the core function and output vocabulary before diving into the nflGame path. The only nonessential element is the marketing-style track-record sentence at the end, which slightly keeps it from a perfect conciseness score.

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?

Given no output schema and only minimal annotations, the description carries the full burden of explaining call patterns, return behavior, and model assumptions. It covers both invocation paths, exact tier names, the fair-value band, what is returned when offeredOdds is omitted, and how legIds are obtained from nflGame. An agent has enough context to invoke the tool correctly in either mode.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful inter-parameter guidance: legPrices are 'used only for the theoretical assemble ceiling,' trueWinProbability and legPrices should be omitted when using nflGame + legIds, and offeredOdds takes precedence over offeredAmerican. These details help an agent choose the correct parameter combination, going beyond the schema.

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 opens with a specific verb+resource: 'Grade a same-game combo ... against its fair value,' and immediately names concrete outputs (fair-value odds band, EV%, negative-correlation-trap flag, 7-tier verdict). It also distinguishes itself from naive pricing by explicitly warning 'never grade EV off the product of the leg prices, which no venue pays,' which separates it from general EV/parlay calculators.

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?

The description gives clear context for both invocation modes: with offeredOdds for EV+verdict, without it for fair value only, and with nflGame for automatic leg retrieval and joint probability computation. It also provides explicit use-case phrases like 'is this combo worth it' and 'grade my parlay quote.' It stops short of explicitly naming sibling alternatives or stating when not to use this tool, so it misses the top bar.

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 toolsInspect
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.

Resources