Skip to main content
Glama

Data Nj

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.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds rich behavioral context: the fill check with market depth, semantic anchor (Jaccard similarity ≥0.30), partition filter (placeholder drops), and response structure. 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 comprehensive but verbose. It front-loads the main purpose and then details each mode, but includes extensive details (fill check, similarity, partition filter) that could be slightly condensed. However, given the tool's complexity, the length is 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?

Despite no output schema, the description comprehensively explains the response format: 'opportunities[]' with fields, partition_check details in event mode, and the fill check conditions. Also covers edge cases (null signals, placeholder filtering). No gaps.

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?

Both parameters have schema descriptions (100% coverage). The description adds examples (e.g., 'fed-decision-may-2026', 'Strait of Hormuz traffic returns to normal'), explains the mode each triggers, and provides additional usage tips. Significantly enhances understanding beyond 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 finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes three modes (trending scan, event-specific, cross-event), each with clear triggers. No ambiguity with sibling tools like polymarket_edges or polymarket_fill_risk.

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?

Explicit usage guidance: 'Call with NO args for trending_scan', 'event (recommended for a specific market)', 'topic (for cross-event scanning)'. Also provides when-not-to-trade via fill check: 'do not trade it' if realizable_edge ≤ 0. Recommends 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 Data Nj 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

A4.1/5.0
Disambiguation4/5

Most tools have distinct purposes, but some overlap exists between ask_pipeworx, ask_pipeworx_grounded, and deep_research, which all query Pipeworx data in different modes. However, their descriptions clearly differentiate them. Similarly, memory and subscription tools are separate. Overall, an agent can distinguish tools with moderate effort.

Naming Consistency4/5

Tool names mostly follow verb_noun pattern with snake_case, such as ask_pipeworx, compare_entities, generate_llms_txt. However, a few tools like 'datasets', 'metadata', and 'query' are single nouns, breaking the pattern. Overall, naming is consistent enough for an agent to predict behavior.

Tool Count3/5

33 tools is above the typical range for an MCP server, but the server covers a wide domain (SEC, FRED, FDA, prediction markets, etc.) with specialized tools. The count is borderline heavy but justifiable given the scope. Some tools like memory and subscription management add to the count but serve necessary auxiliary functions.

Completeness4/5

The tool surface is comprehensive for its intended domain of structured data querying and analysis. It covers data retrieval, entity resolution, comparison, news, subscriptions, and memory. Minor gaps include dependency scanning only for npm and lack of direct web search, but meta-tools like ask_pipeworx fill many needs. Overall, it supports common workflows well.

Resources