Skip to main content
Glama

Unicef

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 the tool as read-only, idempotent, and non-destructive. The description adds extensive behavioral context: caching strategy (1h at KV level), diagnostics fields to explain empty segments, Fed market handling, and the exact edge fields returned. No contradiction 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 comprehensive and well-organized, but slightly verbose with some implementation details (e.g., specific alpha values, funnel counters) that could be omitted for brevity without losing value.

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 the complexity (three segments, multiple filters, output structure) and no output schema, the description fully covers the output format (by_segment, fed, diagnostics), caching, and edge fields. It also explains why certain opportunities are excluded (placeholder filters, Fed note).

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% with each parameter having a description. The description further explains parameter interactions (e.g., min_kelly vs min_partition_leg_kelly, tradeable-edge filters). It adds real-world context like slippage assumptions and Polymarket zero trading fees.

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.' It distinguishes from siblings like polymarket_arbitrage by focusing on edge detection and explicitly targeting 'what should I bet on today' use case.

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 explains the tool is for discovering opportunities without paging through markets, and provides guidance on when to use various knobs (min_liquidity, max_spread_pp). It does not explicitly state when to avoid using the tool but 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 Unicef 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

A3.5/5.0
Disambiguation2/5

Several tool families heavily overlap: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all serve 'find/query Pipeworx data' with blurry boundaries, and the six Polymarket tools (bet_research, polymarket_edges, polymarket_edge_tracker, polymarket_arbitrage, polymarket_fill_risk, polymarket_kalshi_spread) have overlapping purposes. An agent could easily pick the wrong one without reading every description.

Naming Consistency3/5

Most tools follow snake_case verb_noun patterns (list_dataflows, get_data, compare_entities, resolve_entity), and families share prefixes (pipeworx_*, polymarket_*, ask_pipeworx_*). However, the server is named 'Unicef' while almost all tool names reference Pipeworx/Polymarket, and verb choices vary widely, so the overall set lacks a unified naming story.

Tool Count1/5

34 tools is already on the high side, but the real problem is scope: only 3 tools (list_dataflows, dataflow_structure, get_data) relate to the server's stated UNICEF purpose, while the other 31 are an unrelated grab bag of Pipeworx research, prediction-market betting, memory utilities, npm scanning, and llms.txt generation. This is a severe mismatch between count and purpose.

Completeness2/5

For the UNICEF domain implied by the server name, the surface is minimal: browse, structure, and fetch data cover read-only access but nothing else, and the overwhelming majority of tools are off-domain. If the inferred domain is instead 'Pipeworx + prediction markets', coverage is broad, but then the server name is fundamentally misleading and the UNICEF subset is an incomplete afterthought.

Resources