Skip to main content
Glama

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

A4.7/5.0
Behavior5/5

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

Adds significant detail beyond annotations: explains monotonicity and partition-check logic, Jaccard similarity anchor, placeholder filtering, fill check with book depth, and response structure. No contradictions with annotations (readOnlyHint, idempotentHint, destructiveHint).

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?

Well-structured, front-loaded with purpose, clear mode separation. Slightly verbose with technical details, but each sentence adds value. Could be more concise without losing information.

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 thoroughly covers inputs, processing, and response structure (opportunities, partition_check, fill_check). References sibling tool for further steps. Complete for a complex tool.

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?

Schema coverage is 100%, but the description adds rich context: explains the difference between event and topic modes, provides examples, and details algorithmic constraints (similarity threshold, placeholder filter). Adds meaning 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 via monotonicity violations and partition-sum checks. It distinguishes the three modes (trending scan, event-specific, cross-event topic) and differentiates from sibling tools like polymarket_edges and 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 Guidelines4/5

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

Explicit guidance on when to use each parameter (no args, event, topic) with examples. Mentions that for custom sizing, use polymarket_fill_risk. However, lacks direct comparison to similar sibling tools like polymarket_edges for cross-use context.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

Several tools have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are explicitly identical in current behavior, and ask_pipeworx_grounded, validate_claim, and deep_research all overlap with the same underlying routing. The six Polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread, bet_research) share domain and response fields, making misselection likely despite detailed descriptions.

Naming Consistency3/5

Snake_case is used throughout and prefix families (ask_pipeworx_*, nashville_*, polymarket_*, pipeworx_*) are consistent within themselves. However, the overall set mixes verb-first names (ask, compare, remember, subscribe) with noun/adjective-first names (entity_profile, recent_alerts, recent_changes, bet_research), so no single predictable pattern governs all tools.

Tool Count2/5

At 34 tools, the server exceeds a coherent surface, especially for a server named 'Data Nashville' where only 3 of 34 tools actually serve Nashville data. The count is inflated by several largely unrelated feature families (AI visibility, prediction markets, memory, subscriptions), making the set feel like an aggregation of multiple products rather than one focused server.

Completeness3/5

Individual families are fairly complete: memory has remember/recall/forget, subscriptions have subscribe/unsubscribe/list/recent_alerts, and Nashville has discovery/query/recent access. But the overall domain is unclear, and the Nashville-specific surface is thin (no search across datasets, no non-ArcGIS sources), leaving notable gaps relative to the server name.