Skip to main content
Glama

Spoonacular

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?

Annotations already declare readOnly and idempotent hints, but the description adds substantial behavioral detail: 24-hour move warnings, per-sport alpha values, placeholder-slug filters, funnel diagnostics, and a 1-hour KV cache keyed on all knobs. It goes far beyond what annotations alone convey and contains 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.

Conciseness3/5

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

The description is well-structured with uppercase headers and front-loaded purpose, but it is exceptionally long, including exhaustive model internals such as per-sport alphas and threshold gates. While each detail is relevant, the volume exceeds the 'appropriately sized' bar; a leaner version would be more concise.

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?

There is no output schema, so the description must explain return values; it does so thoroughly by specifying by_segment, top-level fields, diagnostics, cached behavior, and Fed exclusions. For a tool of this complexity, the description is complete and self-sufficient.

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?

Schema coverage is 100% for all 9 parameters, so baseline is 3. The description adds value beyond schema by explaining slippage defaults in real-market terms ('20-50bp per trade'), clarifying that min_partition_leg_kelly applies per-leg rather than at parent level, and noting that caching is keyed on all knobs.

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 opens with a specific verb+resource+output: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It further distinguishes itself by detailing three response segments and five model families, making its scope unmistakable and differentiated from sibling tools.

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 clearly states its intended use case: 'Built for "what should I bet on today"' and 'agents discover opportunities without paging hundreds of markets.' It does not explicitly name alternatives or exclusionary conditions, so it stops short of a 5, but the context is unambiguous.

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

All Spoonacular 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

B3/5.0
Disambiguation2/5

The tool set bundles three unrelated domains, and within them several tools are near-indistinguishable: ask_pipeworx_beta is explicitly identical to ask_pipeworx, ask_pipeworx_grounded overlaps with validate_claim, bet_research/polymarket_edges/polymarket_arbitrage all target betting opportunities, and meal_plan_generate duplicates meal_plan_week. The aspect-specific recipe fetchers (ingredients/nutrition/summary/taste) also blur with recipe_information.

Naming Consistency3/5

Most tools follow a reasonable snake_case verb_noun pattern (recipe_search, resolve_entity, compare_entities, unsubscribe), and each cluster (recipe_*, polymarket_*, ask_pipeworx*) is internally consistent. However, conventions fragment across clusters — bare verb memory tools (remember, forget, recall), the ask_pipeworx_beta/_grounded suffix family, and the odd generate_llms_txt — so no single predictable scheme governs the whole surface.

Tool Count2/5

49 tools is far too many for a coherent surface, and crucially the count is misaligned with the server's stated identity: only 18 of 49 tools actually belong to the Spoonacular food domain, while 27 are Pipeworx data/prediction-market tools and 3 are generic memory utilities. The server appears to be three products mashed into one.

Completeness3/5

For the core Spoonacular food domain the surface is reasonably complete — search for recipes/products/ingredients, detail fetchers, meal plans, wine pairing, and unit conversion all exist. But the overwhelming presence of unrelated Pipeworx and memory tools makes the server's actual purpose ambiguous, and gaps are hard to assess when the food tools share the namespace with SEC filings and Polymarket arbitrage.

Resources