Skip to main content
Glama

Itis

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 readOnly, openWorld, idempotent, not destructive. Description adds extensive behavioral context: model families, edge calculation, response structure with by_segment, diagnostics, caching at KV level, Fed bets exclusion. No contradiction.

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?

Fairly long (~300 words) but every sentence adds unique value. Front-loaded with purpose and segmentation. Could be slightly more terse, but dense information justifies length.

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?

For a complex tool with 9 params and no output schema, the description covers input knobs, response structure (by_segment, fed_candidates, diagnostics), edge computation details, and caching. Agent has everything to understand inputs, outputs, and 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?

Schema coverage is 100%, but description adds operational meaning beyond schema descriptions. For example, explains that slippage_pp is subtracted from raw edge before ranking, min_kelly suppresses small opportunities, and min_partition_leg_kelly applies to per-leg Kelly. Very helpful.

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?

Description clearly states 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price', with a specific verb+resource and a use case sentence. Distinguishes from siblings by naming specific segments and hinting at unique capabilities.

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?

Explicitly says 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets'. Does not directly contrast with siblings like polymarket_arbitrage, but purpose is clear enough to decide when to use.

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

All Itis 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 tools occupy overlapping roles: ask_pipeworx and ask_pipeworx_beta are currently identical, ask_pipeworx_grounded/deep_research/validate_claim all provide grounded answering, and bet_research/polymarket_edges/polymarket_arbitrage all surface betting opportunities. The descriptions are detailed, but the boundaries between routers and research modes are fuzzy enough that an agent could easily select the wrong one. The taxonomy, memory, and subscription clusters are distinct, but they are drowned out by the overlapping meta-tools.

Naming Consistency3/5

All names use snake_case, which provides some visual consistency, but the verb_noun pattern is not consistently applied: search_taxa/get_hierarchy are clean verb_noun, while deep_research, entity_profile, polymarket_edges, and bet_research are noun-ish or reversed patterns. There is good family-level consistency within ask_pipeworx_* and polymarket_*, but the overall set mixes conventions and requires reading descriptions to infer what each tool does.

Tool Count2/5

34 tools is well over the 25-tool threshold and reflects a sprawling multi-domain server spanning taxonomy, structured-data lookup, prediction markets, subscriptions, memory, and AI visibility. Each cluster may be individually reasonable, but as a single MCP surface it is too heavy and forces agents to filter through many irrelevant tools.

Completeness4/5

For the broad data-research and prediction-market purpose, the surface is fairly complete: it covers routing, grounded answers, deep multi-source research, entity profiles, comparisons, claim validation, entity resolution, subscriptions, alerts, memory, and market edge/fill checks. Minor gaps exist—no direct web-search tool, the beta router adds no current behavior, and some patent endpoints soft-fail—but agents can generally work around them.

Resources