Skip to main content
Glama

Confluence

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. Changed2 schema fields changed
    • addedInput schema / properties / max_spread_pp
      Added value: +{
+  "description": "Tradeable-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.",
+  "type": "number"
+}
    • addedInput schema / properties / min_liquidity
      Added value: +{
+  "description": "Tradeable-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.",
+  "type": "number"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / min_partition_leg_kelly
      Added value: +{
+  "description": "Minimum 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.",
+  "type": "number"
+}
  3. Changed4 schema fields changed
    • addedInput schema / properties / category_filter
      Added value: +{
+  "description": "Comma-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.",
+  "type": "string"
+}
    • changedInput schema / properties / min_edge_pp / description
      Previous value: -"Minimum |edge| in percentage points to include (default 0.5)."New value: +"Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage."
    • addedInput schema / properties / min_kelly
      Added value: +{
+  "description": "Minimum 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.",
+  "type": "number"
+}
    • addedInput schema / properties / slippage_pp
      Added value: +{
+  "description": "Assumed 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.",
+  "type": "number"
+}
  4. Added

TDQS

A4/5.0
Behavior4/5

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

The description provides extensive behavioral details beyond the annotations (readOnlyHint, etc.), such as caching ('Cached 1h at the KV level'), response structure (by_segment, diagnostics), and internal model logic. It does not contradict the annotations. While very detailed, it adds significant transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

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

The description is excessively long (nearly 600 words) and unstructured as a single paragraph. While detailed, it could be significantly condensed and organized into sections (e.g., purpose, usage, filtering, output) to improve scannability for an AI agent. The 'front-loaded' principle is only partially followed.

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), the description is highly complete. It explains the response structure (by_segment, diagnostics), output fields (e.g., edge_pp_net, kelly_fraction), caching behavior, and even internal model details. An agent would have sufficient context to understand the tool's full behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description mentions 'tradeable-edge knobs' and provides context for parameters like min_liquidity and max_spread_pp, but does not add new parameter information beyond what the schema already provides. The schema descriptions are already thorough.

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's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It uses a specific verb ('scan') and resource ('Polymarket markets'), and the purpose is distinct from sibling tools like polymarket_arbitrage. The description goes further to explain the three model segments, making the tool's function unambiguous.

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 when to use the tool: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It also provides guidance on filtering via tradeable-edge knobs (min_liquidity, max_spread_pp, etc.). However, it does not explicitly mention when NOT to use this tool or compare it to alternatives like polymarket_arbitrage, which would have warranted a 5.

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

All Confluence 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

B3.4/5.0
Disambiguation2/5

The set is dominated by near-overlapping research tools: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all answer factual questions with heavily overlapping descriptions, and the six polymarket_* tools plus bet_research form a second confused cluster. The five confluence_* tools are distinct, but an agent would struggle to pick among the research/betting alternatives without reading thousands of words of caveats.

Naming Consistency2/5

Most names are snake_case, but the conventions are mixed: verb_noun (confluence_create_page, validate_claim), noun_verb (bet_research), prefixed nouns (polymarket_arbitrage, pipeworx_feedback), and bare verbs (recall, forget). The glaring issue is that the server is named Confluence yet only 5 of 36 tools carry the confluence_ prefix, leaving the other 31 tools with no thematic prefix and no consistent pattern.

Tool Count2/5

36 tools is already in the 'too many' range, but the mismatch is deeper: only 5 tools relate to Confluence while 31 tools cover an entirely different domain (Pipeworx data research, prediction markets, subscriptions). For a wiki server this is wildly over-scoped; as a combined surface it is bloated and lacks a unifying purpose.

Completeness2/5

For the Confluence domain the surface is incomplete: pages can be created, fetched, listed, and searched, but there is no update_page, delete_page, comment, attachment, or content-type coverage, leaving obvious CRUD dead ends. For the Pipeworx domain, coverage is broad but disorganized, with overlapping research paths and no clear hierarchy.

Resources