Skip to main content
Glama

Datalastic

by io.github.pipeworx-io

Polymarket Arbitrage

polymarket_arbitrage
Read-onlyIdempotent

Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a trending_scan of the top ~200 markets by weekly volume; pass event for the strongest per-event partition_check, or topic for a themed cross-event scan. event (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). topic (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FILL CHECK: when the partition signal fires, arbitrage.fill_check prices it against live CLOB depth (theoretical_edge_pp_at_book vs realizable_edge_pp at 1000 shares/leg, thin_legs[]) — realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it. For custom sizing use polymarket_fill_risk.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
eventNoSingle-event mode (use this if you know the specific Polymarket event): event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k". Full Polymarket URLs also accepted.
topicNoCross-event mode (use this if you want to scan related events across the platform): a topic or seed question like "Fed rate decision" or "Strait of Hormuz traffic returns to normal". Tool searches Polymarket for related events and checks monotonicity across them.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond annotations stating read-only and idempotent, the description discloses rich behavior: partition filter dropping placeholder slugs, the 3pp threshold for emitting signals, Jaccard similarity anchor, and fill-check behavior against live CLOB depth. It also explains null-signal and skipped_low_similarity responses, with no contradiction to 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 well-organized with labeled sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and front-loaded purpose. Every sentence contributes, but the density might slow quick scanning; a slightly more compact version would earn 5.

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 specifies expected response structure: opportunities[] with key fields, partition_check contents in event mode, and fill-check outputs. It also covers edge cases like skipped_low_similarity, null arb signal, and when the edge is not realizable in the book, making it complete for an agent.

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?

Although the schema covers both parameters, the description adds substantial meaning: accepted URLs for event, example seed questions for topic, what each mode does internally (walks child markets vs searches related events), and how outputs differ per mode. This goes well beyond the schema field descriptions.

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+method: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly distinguishes the two operating modes (event vs topic) and mentions polymarket_fill_risk for custom sizing, separating it from sibling tools within its scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance: recommend event mode for a specific market and topic mode for cross-event scans, with concrete examples and a note about catching date-axis patterns. It also provides a when-not-to-trade rule (realizable_edge_pp <= 0 after fill check) and references polymarket_fill_risk for custom sizing.

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

All Datalastic 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

Several tool clusters have genuinely fuzzy boundaries: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grouned, and deep_research all route to the same 5,767 tools and differ only by use-case nuance, while polymarket_edges, polymarket_arbitrage, and bet_research all surface trading opportunities. scan_competitor_ai_presence is a thin wrapper over ai_visibility_check, and entity_profile, recent_changes, and compare_entities pull overlapping company data. The descriptions are detailed, but an agent can easily select the wrong tool in these clusters.

Naming Consistency4/5

All tools use snake_case and family prefixes are consistent (polymarket_*, pipeworx, datalastic_*, scan_*, ask_*), making the set predictable and readable. The main deviation is verb placement — verb-first (list_subscriptions, resolve_entity, search_within) vs noun-first (entiy_profile, recent_alerts, bet_research) — and prefix position varies between ask_pipeworx and pipeworx_feedback, but these are minor.

Tool Count2/5

33 tools exceeds the heavy threshold, and the count is padded by redundancy: four ask_pipeworx variants that are near-identical, six polymarket tools with overlapping scans, and wrapper tools like scan_competitor_ai_presence that just call ai_visibility_check. The server name suggests maritime focus but only two tools serve that domain, while the rest span a sprawling data-research, prediction-market, AI-visibility, and npm-scanning surface. Consolidating the ask_pipeworx family into one router with a mode parameter and merging wrappers would trim the set to roughly 20 tools without losing capability.

Completeness4/5

The core data-research lifecycle is thoroughly covered: resolve_entity feeds entity_profile, compare_entities, recent_changes, validate_claim, and deep_research, and the prediction-market workflow includes discovery, edge detection, fill-risk validation, and cross-venue analysis. Subscriptions, memory, and feedback are well supported. Minor gaps exist — the datalastic maritime piece has only live position lookups (no history or fleet tools), and one-offs like generate_llms_txt and scan_dependency feel unrelated — but there are no critical dead ends.

Resources