Skip to main content
Glama

Foodish

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

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description goes far beyond by detailing the three model families, edge calculation, tradeable-edge knobs, and caching behavior. This comprehensive disclosure of internal logic and edge cases (e.g., Fed bets note) adds significant transparency beyond what annotations provide.

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 (over 600 words) and dense, covering models, response format, knobs, and diagnostics. While front-loaded with a clear purpose, the extensive detail on model families and caching may overwhelm agents. It could be more concise by reducing model internals and highlighting key points for selection.

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 of 9 parameters, no output schema, and intricate internal logic, the description is remarkably complete. It explains the three segments, edge metrics, tradeable-edge knobs, response top-level with diagnostics, and caching. The agent has enough information to understand what the tool returns and how knobs affect results.

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 coverage is 100%, so baseline is 3. The description adds minimal extra meaning for parameters beyond the schema, focusing more on output structure and internal models. For example, min_partition_leg_kelly gets a bit more context about basket trades, but overall 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 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price' and positions it as a discovery tool for 'what should I bet on today'. This distinct purpose differentiates it from sibling tools like polymarket_arbitrage and polymarket_edge_tracker by focusing on perspective clashes rather than tracking or pure arbitrage.

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 specifies it is for discovering opportunities without paging markets, providing clear context. However, it does not explicitly list when not to use this tool versus alternatives like polymarket_arbitrage, though the sibling list implies other specialized tools exist. The detail about cached data and diagnosis for empty segments helps guide appropriate use.

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

All Foodish 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
Disambiguation5/5

Every tool has a clearly distinct purpose, with detailed descriptions that differentiate between similar-sounding tools like ask_pipeworx, ask_pipeworx_grounded, and deep_research. The Polymarket-related tools each focus on a specific aspect (arbitrage, edges, tracking, fill risk, cross-venue spread), and memory/subscription tools are neatly separated.

Naming Consistency4/5

Most tool names follow a verb_noun or noun_verb pattern with underscores (e.g., ask_pipeworx, validate_claim, resolve_entity). However, there is some inconsistency: single-word names like 'forget' and 'random' mix with multi-word names, and a few names use different structures (e.g., bet_research as noun_noun, random_by_category as adjective_preposition).

Tool Count3/5

32 tools is on the high side for a single server, covering a broad range of functionalities from data queries to betting and memory. While the number might be justified by the platform's scope, it feels heavy, and the server name 'Foodish' suggests a narrower food-focused purpose, creating a mismatch.

Completeness4/5

As a general data platform, the tool set is comprehensive, covering queries, research, entity resolution, memory, subscriptions, and various analytical tools. Minor gaps exist (e.g., no direct editing or upload capabilities), but the core workflows are well-supported. However, the server name 'Foodish' implies food-related tools, which are minimal, so completeness relative to the name is poor.

Resources