Skip to main content
Glama

Bundlephobia

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

A4.4/5.0
Behavior5/5

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

The description goes far beyond the readOnly/idempotent annotations, revealing internal model families, specific thresholds, response fields, diagnostics, and even 1h caching behavior. It also explains why Fed candidates are excluded, providing rich context about the tool's behavior.

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 a dense wall of text with extensive technical details (model formulas, alpha values, threshold changes) that could be moved to documentation. While it has some section headings, it is far too long for a tool description and not front-loaded beyond the first sentence.

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 thoroughly covers the response structure, including by_segment, fed_candidates, and _diagnostics, as well as all filters and caching. It is complete enough for an agent to understand what to expect and why.

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%, so parameters are already well-documented. The description additionally explains the rationale behind key knobs, especially min_partition_leg_kelly and tradeable-edge filters, adding meaning beyond the schema's definitions.

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 opening sentence clearly states the tool scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It also provides a specific use case ('what should I bet on today') and distinguishes itself from siblings by focusing on discovery and data disagreement.

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 frames the tool for discovering bet opportunities without paging hundreds of markets. It also explains how to adjust knobs like slippage and filters to get tradeable edges, but does not explicitly mention alternative tools or when not to use this one.

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

All Bundlephobia 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

A3.9/5.0
Disambiguation2/5

There is substantial overlap among tools in the Pipeworx group: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all route natural-language queries to the same 5,578 tools and sources, with only subtle differences in mode (beta vs stable, grounded vs standard, single vs multi-part). Similarly, polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, and polymarket_fill_risk are heavily intertwined, making differentiation difficult. Tools like similar, size, history, and scan_dependency from the bundlephobia side are distinct, but the Pipeworx family muddies the set.

Naming Consistency3/5

The bundlephobia tools follow a consistent noun pattern (size, similar, history), and the Pipeworx meta-tools use snake_case verbs (ask_pipeworx, resolve_entity, compare_entities, validate_claim). However, the naming is inconsistent across the two families—bundlephobia's simple nouns (size, similar, history) clash with the verbose descriptive verbs—and naming like ai_visibility_check, scan_competitor_ai_presence, and generate_llms_txt break from the Pipeworx pattern. The set mixes short names, camelCase-ish compounds, and snake_case, so no single consistent convention holds.

Tool Count2/5

35 tools is too many for a server that ostensibly serves two domains (bundle-size analysis and Pipeworx data research). The bundle-size analysis needs only a handful (size, history, similar, recent_searches, scan_dependency), yet there are over 30 tools dominated by a sprawling meta-research layer including multiple ask_pipeworx variants, several polymarket tools, plus meta-cognitive tools (remember, recall, forget, discover_tools) that are not core to either domain. This bloats the surface and makes call routing difficult.

Completeness4/5

Each functional domain is fairly complete: bundlephobia covers size measurement, history, alternatives, search, and dependency vetting; the Pipeworx side covers lookup, research, entity resolution, comparison, verification, subscriptions, and feedback. However, there are gaps—e.g., no tool for directly reading an npm package's README or license beyond scan_dependency's summary, and no explicit tools for some administrative actions like account management or subscription editing beyond create/cancel/list. The completeness is strong for what's advertised but not exhaustive.

Resources