Skip to main content
Glama

wikipedia

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

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses substantial behavioral traits: 1-hour KV caching keyed on knobs, placeholder-slug filters, partition overround mechanics, funnel diagnostics in _diagnostics, Fed bets exclusion from ranking, and a 24h-move warning when the edge may already be priced in. It also explains why segments can be empty via diagnostic counters. This goes far beyond what annotations provide.

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 dense and information-rich, with clear section markers (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, etc.) and front-loaded purpose. However, it is quite long and packs many details (e.g., per-sport alpha values, specific gate thresholds) that may be more appropriately placed in the output schema or documentation. It earns its place technically but sacrifices conciseness.

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?

Even without an output schema, the description comprehensively details the response structure: 'RESPONSE TOP-LEVEL: by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note... and _diagnostics{...}' It also explains what each opportunity includes (edge_pp_net, kelly_fraction, etc.) and the caching behavior. For a complex tool with 9 parameters and no output schema, this description fills the gap nearly completely.

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% (all parameters have descriptions), so the baseline is 3. The description adds semantic context by explaining how the knobs interact: '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 behavior: partition arbs always return kelly_fraction_half=0 at the parent level, so min_kelly doesn't filter them but min_partition_leg_kelly does. This adds value 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 clear verb and resource: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It further specifies the tool's intended use ('what should I bet on today') and differentiates it from siblings like polymarket_arbitrage and polymarket_edge_tracker by focusing on Pipeworx data disagreements and the three model-family segments.

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 strong contextual guidance: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It explains when the tool is appropriate and how knobs like min_liquidity/max_spread_pp gate tradeability. However, it doesn't explicitly state when NOT to use it or name direct alternatives (e.g., polymarket_arbitrage for pure arbitrage), so it stops short of full when/when-not clarity.

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

All wikipedia 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
Disambiguation2/5

Several tool families have ambiguous boundaries: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are three variants of the same router (with beta currently identical), and the six polymarket tools plus bet_research heavily overlap in scanning and pricing edges. discover_tools, suggest_questions, and deep_research also all function as 'what should I query' entry points. Agents will struggle to select the right tool without carefully reading long descriptions.

Naming Consistency3/5

Many tools follow a clear verb-first snake_case pattern (get_article_extract, resolve_entity, subscribe, validate_claim), and families like ask_pipeworx_* and polymarket_* are internally consistent. However, notable noun-phrase outliers such as entity_profile, deep_research, bet_research, recent_changes, pipeworx_feedback, and polymarket_edge_tracker break the convention. The naming is readable but not predictable across the full set.

Tool Count2/5

36 tools is well over the 25+ threshold for a typical MCP server, and for a server named 'wikipedia' it is especially disproportionate: only 5 tools actually deal with Wikipedia while 31 are Pipeworx data, prediction-market, memory, subscription, and feedback utilities. The count reflects a broad all-in-one platform crammed into a Wikipedia-labeled surface rather than a well-scoped server. This is a significant scope mismatch.

Completeness4/5

The Wikipedia portion is reasonably complete for read-only lookup: search, summary, sections, full extract, and random discovery cover common encyclopedic questions without dead ends. The broader Pipeworx surface is also extensive, with query, grounded verification, deep research, entity resolution/profile/comparison, claim validation, memory, and subscription lifecycle tools. Minor gaps remain (no article categories/history, no update for subscriptions, no direct fetch of a citation URI), but they are workable.

Resources