Skip to main content
Glama

Noaa Tides

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

A4.7/5.0
Behavior5/5

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

The description extensively discloses behavioral traits beyond the annotations: it details the three response segments, the model families, the calculation of edge_pp_net, Kelly caps, 24h-move warnings, the placeholder-slug filter, partition overround handling, and the caching policy ('Cached 1h at the KV level keyed on all knobs'). It even explains why concentrated_longshot is 'rare-by-design' and why Fed bets are unreliable. The readOnlyHint is consistent with the read-only nature of scanning and ranking.

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 extremely detailed and front-loaded with a clear purpose sentence. It is organized into logical sections (model families, knobs, response structure, diagnostics, caching), but it is verbose. Some details, such as per-sport alpha values and specific funnel counters, may be beyond what an agent needs for selection and invocation. However, given the tool's complexity, the thoroughness is largely justified.

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?

With no output schema, the description fully compensates by explaining the response top-level fields (by_segment, fed_candidates, _diagnostics), what each opportunity carries (edge_pp_net, kelly_fraction, market.liquidity, etc.), and how to interpret empty segments via filter_skips. It also covers edge cases like stale markets and knob behavior, making it complete for an agent to understand both inputs and outputs.

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

Parameters5/5

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

While the schema covers 100% of parameters, the description adds crucial meaning beyond the structured definitions. It explains the 'TRADEABLE-EDGE KNOBS' in context, clarifies that min_partition_leg_kelly applies to per-leg Kelly because partition-level kelly_fraction_half is always 0, and relates slippage_pp to Polymarket's zero-fee but bid/ask spread reality. This is material information not present in the schema.

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 what the tool does: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It identifies the specific verb-environment ('scan ... and return opportunities') and the output structure. This distinguishes it from sibling tools like polymarket_arbitrage or polymarket_edge_tracker by focusing on Pipeworx divergence rather than cross-exchange arbitrage or historical tracking.

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 the intended use case ('Built for "what should I bet on today"') and explains when to use tradeable-edge knobs (e.g., min_liquidity, max_spread_pp) and what they do. It also clarifies that Fed bets are excluded from ranking and why, guiding users on interpretation. However, it does not explicitly name alternative tools or state 'when not to use this tool,' so it falls short of full 5.

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

All Noaa Tides 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

B3.1/5.0
Disambiguation2/5

The 7 NOAA-specific tools (stations, station_metadata, water_level, currents, met_obs, predictions, datums) are clearly distinct, but they are buried among ~31 Pipeworx platform tools with heavy internal overlap: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route factual queries, while polymarket_edges, polymarket_edge_tracker, polymarket_arbitrage, polymarket_fill_risk, and polymarket_kalshi_spread all analyze prediction-market opportunities. An agent cannot easily tell whether the generic question-answering or prediction-market tools are the right choice without reading long descriptions.

Naming Consistency2/5

Most tools use snake_case, but the naming conventions are inconsistent: some use descriptive nouns (stations, datums, predictions), some use noun_verb pairs (water_level, met_obs), and the Pipeworx batch mixes vendor-prefixed names (pipeworx_feedback, pipeworx_trending), bare verbs (remember, forget, recall, subscribe, unsubscribe), and multi-word verbs (generate_llms_txt, scan_competitor_ai_presence, ask_pipeworx_grounded). No predictable pattern unifies the set.

Tool Count1/5

38 tools is far too many for a server named 'Noaa Tides' — only 7 tools relate to NOAA tide/current data, and the other 31 are an unrelated general-purpose data platform (SEC filings, prediction markets, npm packages, AI visibility scanning, memory storage). The overwhelming majority of the surface has nothing to do with the server's stated purpose, making the count and composition a severe mismatch.

Completeness4/5

For the nominal NOAA tides domain, the surface is reasonably complete: station listing, metadata, observed water levels, currents, meteorological observations, tide predictions, and datums cover the core workflows. Minor gaps exist (e.g., no harmonic constituents or extreme water-level statistics tool), but the essential operations are present. The unrelated tools do not fill gaps in the NOAA domain — they are clutter rather than coverage.

Resources