Skip to main content
Glama

artic

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.

TDQS

A4.6/5.0
Behavior5/5

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

The description is rich in behavioral detail: it explains the response structure (by_segment, fed_candidates, _diagnostics), the edge calculation (net slippage, Kelly), filtering logic (tradeable-edge knobs, placeholder filters), and even the 24h-move warning. It also mentions 'Cached 1h at the KV level keyed on all knobs.' Annotations already indicate read-only/idempotent, and the description aligns without contradiction, adding substantial context beyond 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?

The description is a single dense paragraph with run-on sentences and extensive parenthetical details about model families and filters. While it is front-loaded with the core purpose, the sheer volume of details and lack of structured formatting (bullets, headers) makes it less concise than ideal. It is not excessively verbose for a complex tool with no output schema, but it borders on overwhelming.

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, 3 response segments, no output schema), the description is remarkably complete. It outlines the top-level response structure (by_segment, fed_candidates, _diagnostics), per-opportunity fields (edge_pp_net, kelly_fraction, liquidity, etc.), and explains edge cases like empty segments due to stale data or knob filters. It leaves little ambiguous for an AI agent deciding whether and how to call it.

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%, providing baseline 3. The description goes further by explaining the purpose of the knobs: '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.' It also clarifies a subtle interaction (min_kelly not applying to partition arbs) and explains slippage rationale. This adds significant semantic context beyond the parameter descriptions.

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 first sentence clearly states the tool's function: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It also specifies the use case ('Built for "what should I bet on today"'), which distinguishes it from sibling tools like polymarket_edge_tracker (tracking) and polymarket_arbitrage (pure arbitrage). This is a specific verb+resource+scope.

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 explicitly frames when to use the tool: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' This gives clear context for the primary use case. However, it does not explicitly name alternatives or provide when-not-to-use guidance, so it stops short of a 5.

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

All artic 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

A3.8/5.0
Disambiguation2/5

Several clusters of tools heavily overlap: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all answer natural-language questions over the same underlying sources, and six polymarket tools (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, polymarket_edge_tracker, polymarket_kalshi_spread) have blurry boundaries. The four art museum tools are entirely unrelated to the data-research tools, adding confusion to the set.

Naming Consistency3/5

Names are consistently snake_case and generally readable, but the verb-object pattern is not consistent: bare verbs (remember, forget, recall, subscribe) sit alongside verb-first names (get_artwork, validate_claim, resolve_entity) and noun-first compounds (pipeworx_trending, polymarket_edges, ai_visibility_check). The repeated prefixes (ask_pipeworx, polymarket_) do provide some structure.

Tool Count2/5

At 35 tools, the server is overstuffed. The core Pipeworx data and Polymarket analytics surface alone would justify roughly 20 tools, but memory management, subscription lifecycle, llms.txt generation, npm dependency scanning, claim validation, and Art Institute of Chicago lookups are unrelated additions that push the count well beyond a focused scope.

Completeness4/5

Each functional cluster is fairly complete on its own: memory has remember/recall/forget, subscriptions have subscribe/list/recent_alerts/unsubscribe, data lookup has casual, grounded, deep, and validation modes, and prediction markets cover research, edges, arbitrage, fill risk, tracking, and cross-venue spreads. The issue is not missing capabilities but the lack of a single coherent domain.

Resources