Skip to main content
Glama

Data Toronto

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

A4.3/5.0
Behavior4/5

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

Annotations already mark the tool as read-only and idempotent. The description adds significant behavioral context: it walks child markets, checks monotonicity and partition sums, applies semantic similarity filters (Jaccard ≥0.30), and includes fill-check logic against CLOB depth. 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 relatively long but well-organized with clear section headers (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). Key information is front-loaded (three modes). Each sentence adds value, though some minor redundancy exists (e.g., explaining partition_check twice).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (two optional parameters, no output schema), the description provides a thorough overview of behavior, response structure (opportunities array, partition_check details), and failure modes (placeholders, low fill). It covers most agent needs, though a note on rate limits or data freshness would further improve completeness.

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?

Input schema covers 100% of parameters with descriptions. The description enhances this by explaining the behavior of each mode: event triggers partition_check and ordering checks; topic triggers cross-event scanning with semantic anchoring. The additional detail justifies a score above baseline.

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 identifies the tool as finding arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes three modes (no args, event, topic) and contrasts with sibling tools like polymarket_fill_risk, making the purpose unambiguous.

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 states when to use each mode: 'Call with NO args for a trending_scan', 'event (recommended for a specific market)', and 'topic (for cross-event scanning)'. It also advises when not to trade based on fill check results. While it doesn't explicitly compare to siblings, the guidance is clear and actionable.

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

All Data Toronto 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

Multiple query entry points have overlapping boundaries: ask_pipeworx and ask_pipeworx_beta are currently identical, suggest_questions and discover_tools both serve discovery/onboarding, and validate_claim overlaps with ask_pipeworx_grounded. With 34 tools including five Polymarket edge/scanner tools, an agent can easily select the wrong meta-tool despite the detailed descriptions.

Naming Consistency3/5

All names are lowercase snake_case, so there is no style chaos, but the pattern is inconsistent: verb-led names like ask_pipeworx and validate_claim mix with noun-led names like entity_profile, recent_alerts, and polymarket_arbitrage, plus bare memory verbs like remember/recall/forget. Related tools are also not aligned, such as ai_visibility_check vs scan_competitor_ai_presence.

Tool Count2/5

34 tools is too many for a server branded 'Data Toronto', and many tools are only loosely related to the core data-access purpose: ask_pipeworx_beta, generate_llms_txt, scan_dependency, ai_visibility_check, and the memory trio feel like bolt-ons. Even granting Pipeworx's broad research scope, the set is over-stuffed rather than well-scoped.

Completeness4/5

The data-research surface is unusually comprehensive: search, deep research, entity resolution/profiling, comparison, claim validation, alerts/subscriptions, and Toronto open-data querying are all covered. The main gaps are Toronto-side metadata details like resource schemas/columns and a way to browse the full dataset catalogue without a keyword.

Resources