Skip to main content
Glama

Base64

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

A4.5/5.0
Behavior5/5

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

The description adds substantial behavioral context beyond the annotations, including caching at the KV level per knob combination, diagnostic output to explain empty segments, and a 24h-move warning. It explains model families and their assumptions, as well as rare-by-design behavior for concentrated longshots. 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 detailed, covering model families, output structure, and caching. While every sentence adds value, the length may overwhelm agents. It is front-loaded with purpose but could be more concise by trimming redundant explanations of knobs already documented in the schema.

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 tool's complexity (9 parameters, no output schema, nested response), the description is extremely thorough. It explains the by_segment output, fed_candidates, diagnostics, and edge fields like edge_pp_net and kelly_fraction. It also details why Fed bets are excluded and caching behavior, leaving no ambiguity about return values.

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 have descriptions in the input schema (100% coverage). The tool description adds additional context for some parameters (e.g., slippage_pp explains Polymarket fees; min_partition_leg_kelly explains its specific application). However, the description focuses more on the output and methodology than parameter details.

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 for opportunities where Pipeworx data disagrees with market price. It uses specific verbs ('scan', 'return') and distinguishes the tool from siblings like polymarket_arbitrage and polymarket_edge_tracker by focusing on model-driven and structural arbitrage edges.

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 states it is built for 'what should I bet on today' and explains three response segments. It provides guidance on using knobs like min_liquidity and max_spread_pp to filter tradeable edges. However, it does not explicitly compare to alternative tools or state when not to use it.

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

All Base64 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

A3.7/5.0
Disambiguation2/5

Several tool groups have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, polymarket_edges / polymarket_arbitrage / polymarket_edge_tracker / polymarket_fill_risk / polymarket_kalshi_spread / bet_research all push prediction-market opportunities and can be confused, and ai_visibility_check is nested inside scan_competitor_ai_presence. discover_tools and suggest_questions also overlap as tool-discovery entry points.

Naming Consistency3/5

Everything is snake_case and mostly descriptive, but conventions are mixed: verb-first names (resolve_entity, validate_claim, compare_entities, search_within) sit beside noun-first names (entity_profile, recent_changes, bet_research, polymarket_edges), and brand-prefixed tools (pipeworx_feedback, pipeworx_trending) have unprefixed functional siblings (list_subscriptions, recent_alerts). The two actual Base64 tools (base64_encode, base64_decode) don't match the dominant Pipeworx naming style at all.

Tool Count2/5

33 tools is heavy for any single server, and the mismatch is extreme: the server is named 'Base64' yet only 2 of 33 tools relate to encoding/decoding — the other 31 form a sprawling data-research platform. Even judged as a data platform, the count exceeds the comfortable range and includes near-duplicates (the ask_pipeworx family, the Polymarket family).

Completeness4/5

The factual-data surface is well covered: query, grounded lookup, deep research, entity profiling, comparison, claim verification, entity resolution, subscriptions (subscribe/list/unsubscribe/recent_alerts), memory (remember/recall/forget), feedback, and tool discovery all exist with no obvious dead ends. The Base64 encoding domain is also complete (encode/decode across four variants). Minor gaps exist (e.g., no way to update a profile or edit memory entries) but they're workable.

Resources