Skip to main content
Glama

Geoapify

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 already declare readOnlyHint, openWorldHint, idempotentHint as true and destructiveHint false. Description adds significant behavioral context: semantic anchor with Jaccard similarity threshold, partition filter for placeholder slugs, fill check against live CLOB depth, and return of null arb signal when appropriate. 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?

Description is extensive but well-structured with clear sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). Each sentence adds value. Slightly long but justified by tool complexity. Could be slightly tighter, but still efficient given the detail required.

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?

No output schema, so description must explain return values. It does: opportunities array with fields (gap_pp, suggested_trade, etc.), partition_check with sum_yes_prices, gap_from_1, etc., fill check with edge metrics. Covers edge cases (null signals, placeholder filtering, low similarity). Fully equips agent to understand results.

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% with descriptions for both event and topic. Description adds meaning beyond schema: explains event slug format with examples ('fed-decision-may-2026'), topic as seed question, and describes internal logic for each mode (partition_check, comparator, fill check). Examples and behavioral details provide rich semantics.

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?

Description states exactly what the tool does: find arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes three modes (no args, event, topic) with clear verb-resource mapping. Siblings like polymarket_edges and polymarket_edge_tracker have different purposes, so this is well differentiated.

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?

Explicitly states when to use each mode: no args for trending scan, event for specific event, topic for cross-event scanning. Includes guidance on when not to trade (fill check with realizable_edge_pp ≤ 0). Also mentions cross-event catches patterns single-event misses, providing alternative selection rationale.

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

All Geoapify 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

A3.8/5.0
Disambiguation2/5

Multiple tools have overlapping purposes, such as ask_pipeworx, ask_pipeworx_grounded, entity_profile, compare_entities, and validate_claim, all retrieving entity data. Agents may struggle to choose correctly between them. Likewise, bet_research, polymarket_edges, and polymarket_arbitrage cover similar prediction market territory.

Naming Consistency3/5

All tool names use underscores, but the verb/noun order varies: compare_entities (verb_noun), entity_profile (noun_noun), scan_competitor_ai_presence (verb_noun), bet_research (noun_verb). Some names are overly long (scan_competitor_ai_presence). The pattern is readable but not fully consistent.

Tool Count3/5

With 31 tools, the count is high but not extreme. However, the set covers geospatial, data retrieval, prediction markets, npm scanning, and memory/feedback - too broad for a single server. Many tools feel added without clear justification, making the set feel bloated.

Completeness2/5

The geospatial subset is incomplete (missing elevation, distance matrix, isochrones). The data access tools overlap rather than form a complete API surface (e.g., no entity update/delete). Prediction market tools are numerous but redundant. The server tries to do too much and lacks depth in any area.

Resources