Skip to main content
Glama

Csv

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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds extensive behavioral context: caching behavior ('Cached 1h at the KV level'), response structure (three segments under by_segment, diagnostics), edge calculation details (model families, slippage, kelly fractions), and tradeable-edge knobs. No contradictions.

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 verbose but well-structured with clear sections for each model family and response fields. It front-loads the core purpose and then details segments, fields, knobs, and diagnostics. Every sentence adds value, though it could be slightly more concise for a quick scan.

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 (9 parameters, three output segments, diagnostics, no output schema), the description is remarkably complete. It explains edge components, tradeable-edge knobs, diagnostics for empty segments, and cache behavior. The user can understand both the input knobs and the output structure without external documentation.

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?

All 9 parameters have schema descriptions, and the tool description adds rich meaning beyond the schema. For example, it explains that min_liquidity and max_spread_pp are 'Tradeable-edge filters', clarifies the interplay between min_kelly and min_partition_leg_kelly, and provides usage guidance like setting slippage_pp based on market conditions.

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 the tool scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price, using the specific verb 'scan' and resource 'Polymarket markets'. It distinguishes itself from siblings like polymarket_arbitrage and polymarket_edge_tracker by focusing on edge detection via model disagreement.

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 positions the tool for 'what should I bet on today' and notes that agents can discover opportunities without paging hundreds of markets, providing clear context. However, it does not explicitly state when not to use it or compare with alternatives like polymarket_arbitrage.

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

All Csv 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
Disambiguation3/5

Several tools overlap in purpose: ask_pipeworx_beta is explicitly identical to ask_pipeworx today, and the polymarket_* family plus bet_research all touch prediction-market analysis. The descriptions are extremely detailed and mostly disambiguate, but an agent must rely on very long text to avoid misselection.

Naming Consistency3/5

Names are almost all snake_case and readable, but the pattern is mixed: some are verb-first (resolve_entity, list_subscriptions), some noun-first (entity_profile, polymarket_edges), and some are one-word verbs (remember, forget). The ask_pipeworx_* and recent_* prefixes are consistent, but there is no single verb_noun convention throughout.

Tool Count2/5

33 tools is well over the 25+ threshold, especially for a server named 'Csv' that contains only two CSV-specific tools. The rest spans several unrelated domains: data research, prediction markets, subscriptions, memory, AI visibility, and package scanning. The set feels like multiple servers bundled together rather than one well-scoped surface.

Completeness4/5

As a broad data-research platform, coverage is strong: lookup, grounded answers, deep research, entity resolution, profiles, comparisons, fact-checking, subscription lifecycle, and memory persistence are all present. Minor gaps exist, such as no direct fetch tool for pipeworx:// citation URIs and no subscription-update tool, but most workflows have no dead ends.

Resources