Skip to main content
Glama

Emsc

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

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description goes beyond by detailing caching behavior (cached 1h at KV level), the diagnostic output (_diagnostics) for understanding why segments are empty, and the algorithmic methodology (including placeholder-slug filters and Kelly calculations). No contradictions 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.

Conciseness3/5

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

The description is very long and includes extensive technical detail (e.g., exact algorithm parameters, placeholder-slug lists, diagnostic funnel counters) that could be condensed or moved to an optional documentation. However, it is well-structured with clear sections for purpose, segments, knobs, and response, and front-loads the core use case.

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?

Despite no output schema, the description fully explains the response structure (by_segment, diagnostic fields, Fed bets note) and covers edge calculation, knobs, filtering logic, caching, and limitations. All 9 parameters are explained, and the tool's complexity is addressed comprehensively.

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?

All 9 parameters are fully described in the input schema (100% coverage). The description adds functional context by explaining the purpose of key knobs (e.g., 'min_liquidity / max_spread_pp drop opportunities where edge isn't realizable') and how they interact with tradeability, which enhances understanding beyond the schema alone.

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 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price' and explicitly identifies the target use case as 'what should I bet on today'. It differentiates from sibling tools by detailing the specific algorithmic segments (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) and the response structure, making the purpose highly specific and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implicit context ('Built for...discover opportunities') but lacks explicit guidance on when to use this tool versus its siblings (e.g., polymarket_arbitrage, polymarket_edge_tracker). No direct alternatives or exclusion criteria are mentioned, leaving an agent to infer usage from the detailed output structure.

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

All Emsc 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

A4/5.0
Disambiguation3/5

Multiple tools overlap: ask_pipeworx and ask_pipeworx_beta are currently identical, and the five prediction-market tools (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, polymarket_edge_tracker) cover adjacent tasks that require careful reading. However, descriptions are unusually explicit about when to prefer each, and non-overlapping domains (memory, subscriptions, earthquakes, npm) are clearly separated.

Naming Consistency4/5

All tool names are snake_case with a mostly verb-first pattern (ask_, compare_, discover_, generate_, list_, scan_, search_, validate_), making the surface predictable. Minor deviations like deep_research, entity_profile, and single-word verbs (remember, recall, forget) break the pattern slightly, but each family is internally consistent.

Tool Count2/5

33 tools exceeds the 25+ threshold for 'too many,' and several could be consolidated — ask_pipeworx_beta is redundant today, and the prediction-market suite could fold into 2-3 tools. The count reflects a genuinely wide data platform with meta-tools (discover_tools, suggest_questions, ask_pipeworx) already covering discovery, so the surface feels heavy for an agent to triage.

Completeness4/5

Core workflows are well covered: querying (ask_pipeworx, grounded, deep_research), research profiles (entity_profile, compare_entities, recent_changes), input resolution (resolve_entity), fact-checking (validate_claim), memory lifecycle, and subscription lifecycle all have complete loops. Minor gaps exist, notably no tool to fetch a pipeworx:// citation URI directly (search_within expects already-fetched text), and some one-off tools like generate_llms_txt and scan_dependency feel bolted on.

Resources