Skip to main content
Glama

Ebi Ols

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?

Annotations declare readOnlyHint and idempotentHint, so the safety profile is known. The description adds substantial behavioral context beyond annotations: response structure with by_segment, diagnostic counters, 1-hour caching keyed on knobs, exclusion of Fed bets with reasoning, and the 24h-move warning. 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.

Conciseness4/5

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

The description is long but densely packed with necessary information for a complex tool. It is front-loaded with purpose and then details response structure and knobs. However, it could be improved with headings or bullet points to increase scannability; it currently reads as a wall of text.

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 no output schema, the description thoroughly defines the response top-level fields, per-opportunity fields, diagnostics, and caching behavior. It explains why certain segments might be empty and how to interpret warnings. This is complete enough for an agent to understand what to expect and how to act on results.

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%, so baseline is 3, but the description adds value by grouping parameters into 'TRADEABLE-EDGE KNOBS' and clarifying the distinction between min_kelly and min_partition_leg_kelly (for partition arbs, parent kelly is 0). It also explains when to adjust slippage_pp, which is not fully captured in 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 opening sentence clearly states the tool's function: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' This gives a specific verb, resource, and scope, and the detailed description of model families and output segments distinguishes it from sibling tools like polymarket_arbitrage and polymarket_edge_tracker.

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 frames usage with 'Built for "what should I bet on today"' and provides concrete guidance on parameter tweaks, such as 'Set to 5000 to drop thin-book opportunities' and 'Bump for very thin partitions.' It doesn't explicitly mention when NOT to use this tool or name alternatives like polymarket_arbitrage, but the context is clear.

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

All Ebi Ols 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

B3.3/5.0
Disambiguation2/5

Many tools have overlapping purposes, especially among Pipeworx query tools (ask_pipeworx, ask_pipeworx_grounded), betting research tools (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_kalshi_spread), and memory tools (remember, recall, forget). An agent could easily select the wrong tool. Additionally, tools like 'discover_tools', 'search', and 'search_within' have unclear boundaries.

Naming Consistency3/5

Most tool names use snake_case (e.g., 'entity_profile', 'validate_claim'), but there are inconsistencies with single-word verbs like 'forget', 'recall', 'remember', 'subscribe', 'unsubscribe', and the mixed pattern of 'ask_pipeworx' vs 'pipeworx_feedback'. Overall, the naming is somewhat consistent but not fully predictable.

Tool Count3/5

With 32 tools, the server has a high but not extreme count. However, the tools span multiple unrelated domains (ontologies, financial data, betting, memory, subscriptions, AI visibility), making the server feel like a collection of disparate features rather than a focused toolset. This reduces the appropriateness of the count for a single server.

Completeness2/5

The tool surface has significant gaps. For example, ontology tools lack create/update/delete operations; betting tools only provide research and analysis but no placement; memory tools allow save/recall/delete but not update; and there is no tool for user authentication or account management despite subscription features. The server covers many areas but none completely.

Resources