Skip to main content
Glama

Celestrak

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

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description details the three model segments, edge calculation (net of slippage, Kelly fractions), response structure (diagnostics, Fed note), and caching behavior ('Cached 1h at the KV level'). It also mentions limitations like the unreliability of Fed bets without paid data. No contradictions with annotations.

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 long but efficiently packed with information. It is structured by segments (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) and response fields, making it scannable. Every sentence adds essential detail. Minor verbosity in technical explanations could be trimmed, but it's justified by the tool's complexity.

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 tool's complexity (9 parameters, three model families, diagnostics, tradeable-edge knobs), the description completely covers what the tool does, its input knobs, output structure, and behavioral nuances. Without an output schema, it adequately explains the return fields and diagnostics so agents can parse the response.

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?

The input schema already describes all 9 parameters (100% coverage). The description adds value by explaining usage context (e.g., 'min_kelly' skips small opportunities, 'slippage_pp' subtracts from edge, 'min_partition_leg_kelly' applies per-leg for partitions). However, not every parameter gets individual elaboration in the description; some are only covered by 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 the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It specifies the verb 'scan' and the resource 'Polymarket markets' with a distinct outcome (disagreement detection). The mention of 'Built for "what should I bet on today"' distinguishes it from siblings like polymarket_arbitrage or polymarket_edge_tracker, which focus on specific subsets.

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 provides clear context on when to use (to discover opportunities) and explains the tradeable-edge knobs (min_liquidity, max_spread_pp) that help decide viability. However, it does not explicitly state when not to use this tool or suggest alternative tools for other scenarios, such as if a specific arbitrage is needed.

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

All Celestrak 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

The tool set mixes several distinct domains (satellite orbital data, Pipeworx data routing, prediction-market analysis, memory management, subscriptions), but within the Pipeworx umbrella there is heavy overlap: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all route natural-language questions to the same underlying 5,756 tools. An agent could easily misselect between them, especially since ask_pipeworx and ask_pipeworx_beta are described as currently identical.

Naming Consistency3/5

Many tools follow a clear verb_noun pattern (list_subscriptions, create... none, but compare_entities, resolve_entity, generate_llms_txt, scan_dependency, subscribe/unsubscribe, remember/recall/forget), yet the naming is inconsistent across the set: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, get_satellite, get_group, recent_alerts, recent_changes, entity_profile, and deep_research do not share a uniform convention. CamelCase appears in polymarket_arbitrage, polymarket_edges, etc. while most others are snake_case, and the satellite tools (get_satellite, get_group, search_by_name) form a distinct sub-pattern that clashes with the Pipeworx meta-tools.

Tool Count2/5

34 tools is on the heavy side, and the effective surface is bloated: there are three variants of ask_pipeworx, four polymarket_* tools, three satellite-specific tools that are unrelated to the server's apparent core purpose, and several meta/utility tools (remember, recall, forget, pipeworx_feedback, pipeworx_trending, suggest_questions) that could be consolidated or are only tangentially related. The count itself is not extreme, but the scope is muddled: the server claims the name Celestrak (satellite tracking) while the overwhelming majority of tools are for Pipeworx data access and prediction markets, making the tool count feel inappropriate for either purpose.

Completeness3/5

For the Pipeworx data-access domain, the tool set is quite thorough: natural-language routing, grounded answers, deep research, entity profiling, entity comparison, claim verification, semantic search, and tool discovery are all present. However, there are notable gaps: the subscription lifecycle lacks an update/resume mechanism, and the satellite domain (the server's namesake) is severely incomplete — only three lookup tools with no live tracking, no group listing beyond a handful of groups, and no clear lifecycle CRUD. The memory tools (remember/recall/forget) are minimal but complete for their narrow scope.

Resources