Skip to main content
Glama

Exa

by io.github.pipeworx-io

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 (after slippage), 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.

Input Schema

TableJSON 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.
slippage_ppNoAssumed execution slippage in percentage points per leg (default 0.3). Subtracted from raw |edge| before ranking and Kelly sizing. Polymarket has zero trading fees as of 2024 but bid/ask + thin depth typically eats 20-50bp per trade. Bump for very thin partitions; drop to 0 if you have a smarter fill model.
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. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds extensive behavioral context: detailed model families, response segments, tradeable-edge filters, caching (1h at KV level), diagnostics, and explanation of output fields like edge_pp_net, kelly_fraction, and 24h-move warning. It also explains rare conditions for concentrated_longshot. No contradiction with annotations.

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 comprehensive but verbose (several paragraphs). However, it is well-structured with clear headings (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT, TRADEABLE-EDGE KNOBS, RESPONSE TOP-LEVEL). The main purpose and usage are front-loaded. Could be slightly more concise, but the structure earns a 4.

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 the tool's complexity (9 parameters, no output schema, multiple model families), the description is very complete. It covers all response segments, diagnostics, caching, and special cases (Fed bets, thin partitions). It also explains the output fields and their meaning. No gaps found.

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

Parameters5/5

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

Schema coverage is 100%, so baseline is 3. However, the description adds substantial meaning beyond schema: default values, acceptable ranges, effects on results (e.g., slippage_pp explains Polymarket fees, min_partition_leg_kelly explains why min_kelly doesn't filter partition arbs). It also provides examples like 'Set to 5000 to drop thin-book opportunities'. This makes the parameters highly understandable.

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 clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price'. It specifies the verb (scan/return), resource (Polymarket markets with Pipeworx disagreement), and distinguishes from siblings like polymarket_arbitrage and polymarket_edge_tracker by focusing on edge detection. The use case 'what should I bet on today' is immediately clear.

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 provides clear context on when to use (discover opportunities without paging) and includes guidance on edge knobs like min_liquidity and max_spread_pp. It also mentions Fed bets are excluded from ranking with a reason. However, it does not explicitly compare to sibling tools or state when not to use this tool.

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

All Exa toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Several tools share the same basic purpose: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions to data sources, and ask_pipeworx_beta is currently identical to ask_pipeworx. The polymarket_* family has five overlapping tools (edges, arbitrage, edge_tracker, fill_risk, kalshi_spread), though detailed descriptions and explicit 'use when' guidance help separate them. Overall, an agent can generally pick the right tool but faces real ambiguity in the query-router and betting clusters.

Naming Consistency4/5

Most tools follow a clear verb_noun snake_case convention (search, get_contents, resolve_entity, validate_claim, subscribe, unsubscribe). However, several noun-first names break the pattern: entity_profile, ai_visibility_check, pipeworx_feedback, pipeworx_trending, and the polymarket_* family, plus adjective-noun names like recent_alerts and recent_changes. The deviations are readable and mostly clustered around product-specific domains, so the inconsistency is minor.

Tool Count2/5

At 34 tools, this significantly exceeds the 25+ threshold for a heavy tool surface. The server bundles four distinct domains — web search, structured data routing, prediction-market analysis, and memory/subscriptions — into one MCP endpoint, which inflates the count. While each domain has some justification, a more focused split into separate servers would yield better coherence.

Completeness4/5

The surface is remarkably thorough for its blended scope: search has query/retrieve/similar/within, structured data has default/grounded/beta/deep-research modes, subscriptions have full lifecycle coverage, and memory has save/recall/delete. Minor gaps exist, such as no subscription-update tool and no direct pipeworx:// URI reader in the tool list, but these are workable. The prediction-market and entity-analysis workflows are covered end to end.

Resources