Skip to main content
Glama

Overpass

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?

The description goes far beyond the readOnly/idempotent annotations by disclosing caching ('Cached 1h at the KV level keyed on all knobs'), the response structure (by_segment, fed_candidates, _diagnostics), model-specific behavior (e.g., placeholder-slug filters, halved Kelly, 24h-move warning), and design limitations (Fed signal unreliable). This gives the agent an accurate picture of side effects and outputs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is an extremely dense, single-paragraph block with ALL-CAPS emphasis and no bullet points or line breaks. It contains valuable information but is not front-loaded or scannable; an agent must parse a large wall of text before reaching the key parameters. It could be significantly tightened while retaining the essential details.

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 a complex multi-segment response, the description compensates by explicitly enumerating the response top-level keys, diagnostics fields, and per-opportunity attributes. It also explains why segments might be empty and how knobs affect results, providing a complete mental model for the tool's behavior.

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?

Even though the schema documents all 9 parameters (100% coverage), the description adds critical semantic context: it explains that min_partition_leg_kelly applies per-leg rather than parent-level because partition arbs return kelly_fraction_half=0 at parent level, clarifies the 'tradeable-edge' knobs, and provides execution-slippage rationale ('Polymarket has zero trading fees as of 2024 but bid/ask + thin depth typically eats 20-50bp per trade'). This goes beyond the schema's literal field definitions.

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 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price,' which specifies the action, resource, and goal. It also states its intended use case ('what should I bet on today'), clearly distinguishing it from sibling tools like polymarket_arbitrage or polymarket_edge_tracker by focusing on disagreement with Pipeworx data.

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 it: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It provides context for discovery but does not explicitly name alternatives or state when not to use it, 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 Overpass 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
Disambiguation3/5

Most tools have distinct purposes, but the ask_pipeworx trio (stable, beta, grounded) are near-identical variants, and the five polymarket_* tools plus bet_research heavily overlap in the edge-finding space. Detailed descriptions help, but an agent could easily misselect among these clusters.

Naming Consistency3/5

Names are all snake_case and readable, but conventions vary: ask_pipeworx_* uses a prefix pattern, polymarket_* is consistent, yet others mix verbs (scan_competitor_ai_presence, generate_llms_txt) with nouns (entity_profile, resolve_entity). No single verb_noun pattern governs the set.

Tool Count2/5

34 tools is well above the 25-tool threshold and feels like multiple servers merged into one: structured data routing, prediction markets, OSM, memory, subscriptions, and AI-visibility checks. The breadth is impressive but the count is heavy for a single tool surface.

Completeness4/5

The surface is notably complete for its blended domain: memory has remember/recall/forget, subscriptions have subscribe/list/unsubscribe, data access has multiple router modes plus deep research and claim validation, and prediction markets have research, edge, arbitrage, fill-risk, and cross-venue tools. Minor gaps exist (no subscription update, no explicit reverse-geocoding tool), but core workflows are covered.

Resources