Skip to main content
Glama

Polymarket Edges

polymarket_edges
Read-onlyIdempotent

Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today", agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped into three response segments under by_segment: (1) MODEL_DRIVEN, crypto_price (lognormal barrier from 90d FRED log-returns) and news_momentum (GDELT 7d/21d article-volume ratio, soft signal w/ halved Kelly). (2) STRUCTURAL_ARBITRAGE, partition_overround on mutually-exclusive events; per-leg favorite-longshot bias correction with per-sport α (tennis 1.02, soccer 1.10, MMA 1.15, default 1.0); placeholder-slug filter drops will-person-X / will-team-Y / will-manager-Z / will-someone-else- backstops; partitions with >20% placeholder fraction skipped entirely. (3) CONCENTRATED_LONGSHOT, basket trade when one leg ≥75% AND ≥2 longshots ≤8% AND portfolio return ≥25:1; rare-by-design (gates relaxed Run 8 from prior 85%/5%/50:1). EVERY OPPORTUNITY carries edge_pp_net (net of slippage AND Polymarket's own taker fee, fees_pp_applied itemises the fee component; see fees.ts for the published per-category schedule), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume, plus a 24h-move warning ("Market moved X.Xpp in 24h") when the recent move alone exceeds the edge, your edge may already be in the price. TRADEABLE-EDGE KNOBS: min_liquidity / max_spread_pp drop opportunities where edge isn't realizable; min_partition_leg_kelly filters partitions by best per-leg Kelly. RESPONSE TOP-LEVEL: by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note (Fed bets surface here, excluded from ranking, 1m-T vs EFFR signal is unreliable at meeting-month horizons without paid OIS/SOFR-futures data), and _diagnostics{concentrated_longshot:{...funnel counters},category_counts,filter_skips} so callers can see WHY a segment is empty (top-N stale, all candidates failed gates, knob dropped them). Cached 1h at the KV level keyed on all knobs.

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": {
      "limit": 5,
      "window": "1wk"
    },
    "name": "polymarket_edges"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoTop N edges to return after ranking. Default 10, max 25.
windowNoPolymarket volume window to filter markets. Default 1wk.
min_kellyNoMinimum half-Kelly fraction (as decimal, e.g. 0.005 = 0.5% of bankroll) to include single-leg opportunities. Default 0 (no filter). Skips opportunities that are too small to bet sensibly even if the edge is large.
min_edge_ppNoMinimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage and Polymarket's own taker fee.
slippage_ppNoAssumed execution slippage in percentage points per leg (default 0.3), for bid/ask + thin depth cost that a last-trade price does not show. Subtracted from raw |edge| before ranking and Kelly sizing, ON TOP OF Polymarket's own taker fee, which is NOT zero (rate 0.04-0.07 depending on category, read off each market's own published fee schedule; see fees_pp_applied on every row and fees.ts for the full schedule). Bump slippage for very thin partitions; drop to 0 if you have a smarter fill model, the fee still applies regardless.
max_spread_ppNoTradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books, anything wider eats most plausible edges.
min_liquidityNoTradeable-edge filter. Minimum $ liquidity on the representative market (or for partition_overround, on at least one top_leg). Default 0 (no filter). Set to 5000 to drop thin-book opportunities where executing the edge would walk the book past breakeven.
category_filterNoComma-separated list to restrict the output: "model_driven" (crypto_price + news_momentum), "structural_arbitrage" (partition_overround), "concentrated_longshot". Combine like "model_driven,structural_arbitrage". Default: all.
min_partition_leg_kellyNoMinimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at the parent level by design (basket trades don't compose to single-leg Kelly), so min_kelly never filters them, this knob applies to the per-leg Kelly inside top_legs instead. Use to suppress thin partitions whose individual leg edges aren't worth the per-leg slippage cost.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / max_spread_pp / description
      Previous value: -"Tradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books — anything wider eats most plausible edges."New value: +"Tradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books, anything wider eats most plausible edges."
    • changedInput schema / properties / min_partition_leg_kelly / description
      Previous value: -"Minimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at the parent level by design (basket trades don't compose to single-leg Kelly), so min_kelly never filters them — this knob applies to the per-leg Kelly inside top_legs instead. Use to suppress thin partitions whose individual leg edges aren't worth the per-leg slippage cost."New value: +"Minimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at the parent level by design (basket trades don't compose to single-leg Kelly), so min_kelly never filters them, this knob applies to the per-leg Kelly inside top_legs instead. Use to suppress thin partitions whose individual leg edges aren't worth the per-leg slippage cost."
    • changedInput schema / properties / slippage_pp / description
      Previous value: -"Assumed execution slippage in percentage points per leg (default 0.3), for bid/ask + thin depth cost that a last-trade price does not show. Subtracted from raw |edge| before ranking and Kelly sizing, ON TOP OF Polymarket's own taker fee — which is NOT zero (rate 0.04-0.07 depending on category, read off each market's own published fee schedule; see fees_pp_applied on every row and fees.ts for the full schedule). Bump slippage for very thin partitions; drop to 0 if you have a smarter fill model — the fee still applies regardless."New value: +"Assumed execution slippage in percentage points per leg (default 0.3), for bid/ask + thin depth cost that a last-trade price does not show. Subtracted from raw |edge| before ranking and Kelly sizing, ON TOP OF Polymarket's own taker fee, which is NOT zero (rate 0.04-0.07 depending on category, read off each market's own published fee schedule; see fees_pp_applied on every row and fees.ts for the full schedule). Bump slippage for very thin partitions; drop to 0 if you have a smarter fill model, the fee still applies regardless."
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "limit": 5,
      +    "window": "1wk"
      +  }
      +]
  3. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare it read-only, idempotent and non-destructive, yet the description still adds substantial behavior: 1h KV caching keyed on all knobs, edge computed net of both slippage and Polymarket's own taker fee (0.04-0.07 by category), Kelly capped at 0.25, a 24h-move warning, and fed_candidates excluded from ranking because the EFFR signal is unreliable at meeting-month horizons. The _diagnostics block explicitly tells callers why a segment may be empty. No contradictions with the annotations.

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?

Purpose and the by_segment structure are front-loaded, which is good, but the body is a wall of implementation internals that no caller needs to invoke the tool: per-sport alpha constants (tennis 1.02, soccer 1.10, MMA 1.15), 'gates relaxed Run 8 from prior 85%/5%/50:1', placeholder-slug patterns, and a pointer to fees.ts. Those sentences consume attention without improving tool selection or argument choice.

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?

With no output schema and nine parameters, the description carries the return-shape burden and does so: it enumerates the top-level keys (by_segment with three named children, fed_candidates/fed_note, _diagnostics), the per-opportunity fields (edge_pp_net, fees_pp_applied, kelly_fraction/_half, market.liquidity/spread_pp/volume), and the caching behavior. Nothing an agent needs to call or interpret the result is missing.

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 a baseline of 3 applies; the description earns above that by explaining the knob interactions the schema states only in isolation, notably that min_kelly never filters partitions because parent-level kelly_fraction_half is 0 by design, so min_partition_leg_kelly must be used instead, and that min_liquidity checks 'at least one top_leg' for partitions. It does not add format/syntax detail beyond the schema.

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?

Opens with a specific verb+resource+scope: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price', and names the intended question ('what should I bet on today'). The three named response segments further pin down what is returned. It never differentiates itself from close siblings such as polymarket_arbitrage or polymarket_edge_tracker, so an agent cannot route between them from this text alone.

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?

Gives clear situational guidance, including concrete conditional advice for the tradeable-edge knobs ('Set to 2 to require tight books', 'Set to 5000 to drop thin-book opportunities') and explains the rare-by-design nature of the concentrated_longshot segment. It does not state when NOT to use it or which sibling to prefer for overlapping tasks, so it stops short of full exclusion guidance.

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.