Skip to main content
Glama

Cactus

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

A5/5.0
Behavior5/5

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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses internal heuristic details: Jaccard similarity threshold of ≥0.30, placeholder fraction filter (>20% returns null), the 3pp deviation threshold for partition signals, and the fill-check distinction between theoretical and realizable edge. It also warns 'do not trade it' when realizable edge ≤0, which is critical behavioral context. No contradiction 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy but densely packed with valuable information, using clear structural labels (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK, Response) to organize sections. It opens with a one-sentence purpose, then methodically covers modes, heuristics, filters, and output format. Every sentence serves a purpose, and the structure aids scanning without redundancy.

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 (three modes, multiple heuristics, response structure, fill-check caveat) and the absence of an output schema, the description is remarkably complete. It explains inputs, processing, filters, response fields, and trading advice, and even references a sibling tool for deeper risk modeling. No significant gaps remain for an agent to invoke the tool correctly.

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 input schema already covers both parameters with 100% description coverage, the tool description adds substantial extra meaning. It explains what an 'event' slug looks like, that full URLs are accepted, how 'topic' searches related events, and what the no-args default does. It also details the internal processing for each parameter (e.g., walking child markets, partition checks, cross-event flattening), enriching the schema far beyond simple type/description.

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 tool from siblings by naming the exact mechanism and pointing to polymarket_fill_risk for a complementary capability. This leaves no ambiguity about what the tool does and how it differs from related tools.

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?

The description explicitly states when to use each invocation mode: 'Call with NO args for a trending_scan...', 'pass event...', or 'topic...'. It gives a recommendation ('event (recommended for a specific market)') and contrasts cross-event vs single-event use cases. It also addresses when not to trade and directs users to polymarket_fill_risk for custom sizing, effectively covering both when-to-use and alternatives.

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

All Cactus 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
Disambiguation3/5

Most tools have clearly differentiated roles, but several pairs blur boundaries: ask_pipeworx and ask_pipeworx_beta are currently functionally identical, and identify vs resolve both wrap the same NCI CACTUS service. The detailed descriptions rescue most selections, but an agent could easily mispick between the research and chemical lookup options.

Naming Consistency3/5

Names are mostly snake_case and readable, but conventions are mixed: some are verb-first (ask_pipeworx, validate_claim, search_within) while many are noun-first or domain-prefixed (entity_profile, polymarket_edges, recent_changes, pipeworx_trending). There is no single predictable pattern for a new tool's name, though subfamilies (polymarket_*, ask_pipeworx_*) are internally consistent.

Tool Count3/5

At 33 tools, this is well above the typical well-scoped range and carries real selection overhead. The unusually broad purpose—a data router plus prediction-market analysis, memory, subscriptions, and several standalone utilities—partially justifies the count, but it still feels heavy and could be consolidated.

Completeness4/5

For its varied subdomains, coverage is strong: memory has remember/recall/forget, subscriptions have subscribe/unsubscribe/list/recent_alerts, and prediction markets span research, edge scanning, arbitrage, fill-risk, and edge telemetry. Minor gaps exist—such as no direct tool to fetch a specific citation URI by identifier, and the redundant stable/beta router pair—but there are no obvious dead ends.

Resources