Skip to main content
Glama

Findymail

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

A4.6/5.0
Behavior5/5

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

The description adds extensive behavioral context beyond annotations: it details caching (1h at KV level keyed on knobs), the three model families with their internal mechanics (e.g., lognormal barrier, GDELT ratio, partition overround with sport-specific alpha), response structure (by_segment, fed_candidates, _diagnostics), and edge attributes (edge_pp_net, kelly_fraction, 24h-move warning). Annotations already declare readOnlyHint and idempotentHint, which this description fully supports without contradiction.

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 lengthy but well-organized with sections for each model family, knobs, and response structure. It uses clear labels (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) and bullet-like formatting. Some repetition (e.g., explaining partitions multiple times) could be trimmed, but overall it is front-loaded with purpose and efficiently packs detailed information.

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 9 parameters (all fully described in schema), no output schema, and high complexity (three segments, multiple filters, diagnostics), the description is remarkably complete. It covers caching, the exact attributes returned per opportunity (edge_pp_net, kelly_fraction, etc.), the fed_candidates exclusion, and diagnostic counters. An agent has sufficient information to invoke the tool and interpret results correctly.

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 schema descriptions (100% coverage), so the baseline is 3. The description adds value by explaining knobs like max_spread_pp ('tight books'), min_liquidity ('walk the book past breakeven'), and min_partition_leg_kelly (why min_kelly doesn't apply to partition arbs). For slippage_pp, it adds context about zero fees but typical bid/ask impact. This extra explanation justifies a score above baseline.

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 Polymarket markets to find opportunities where Pipeworx data disagrees with market price, using the phrase 'what should I bet on today'. It specifies the action (scan, return), the resource (Polymarket markets), and the scope (discrepancies with Pipeworx data). This distinguishes it from sibling tools like polymarket_edge_tracker which tracks edges over time.

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 implies usage for discovering betting opportunities without paging through hundreds of markets, and explains the three response segments and adjustable knobs. However, it does not explicitly state when not to use this tool versus alternatives like polymarket_arbitrage or polymarket_fill_risk, leaving some ambiguity for an agent.

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

All Findymail 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

A3.8/5.0
Disambiguation2/5

Several tools have heavily overlapping purposes: ask_pipeworx and ask_pipeworx_beta are currently identical, deep_research/validate_claim/ask_pipeworx all route factual questions to the same underlying catalog, and ai_visibility_check is essentially wrapped by scan_competitor_ai_presence. The long descriptions help, but the boundaries between query, research, and verification tools are genuinely ambiguous.

Naming Consistency2/5

Names are all lowercase snake_case, but there is no consistent verb_noun or domain pattern: ask_pipeworx, findymail_find_email, scan_competitor_ai_presence, polymarket_kalshi_spread, and generate_llms_txt each use a different structural convention. The mix of brand prefixes, domain prefixes, and bare commands makes the naming feel ad hoc rather than systematic.

Tool Count2/5

33 tools is well over the 25+ threshold and reflects a server that bundles at least five distinct concerns: email lookup, structured data research, prediction-market analysis, subscriptions, and memory. Most individual tools earn their place, but the count is too high for coherent tool selection in a single MCP server.

Completeness3/5

Coverage is broad and mostly self-sufficient for the Pipeworx data ecosystem: querying, deep research, entity resolution, comparisons, verification, subscriptions, memory, and one-off utilities are all present. There are notable gaps though—there is no tool to fetch a full record from a returned pipeworx:// citation URI, and the Findymail side is limited to find/reverse with no verification or bulk capability.

Resources