Skip to main content
Glama

Emsc

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.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • removedInput schema / anyOf
      Removed value: -[
-  {
-    "required": [
-      "event"
-    ]
-  },
-  {
-    "required": [
-      "topic"
-    ]
-  }
-]
  2. Changed3 schema fields changed
    • addedInput schema / anyOf
      Added value: +[
+  {
+    "required": [
+      "event"
+    ]
+  },
+  {
+    "required": [
+      "topic"
+    ]
+  }
+]
    • changedInput schema / properties / event / description
      Previous value: -"Single-event mode: Polymarket event slug (e.g. \"when-will-bitcoin-hit-150k\") or full URL."New value: +"Single-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."
    • changedInput schema / properties / topic / description
      Previous value: -"Cross-event mode: a topic or seed question. Tool searches Polymarket for related markets across separate events and checks monotonicity across them. E.g. \"Strait of Hormuz traffic returns to normal\"."New value: +"Cross-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."
  3. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds extensive behavioral context: details of scanning logic (monotonicity, partition checks), filtering mechanisms (semantic anchor, partition filter, fill check), and rules for interpreting results. 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.

Conciseness4/5

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

The description is well-structured with clear sections (modes, semantic anchor, partition filter, response, fill check). It is front-loaded with the core purpose. While it is somewhat lengthy, every sentence adds necessary detail for correct tool usage. A minor trim could improve conciseness.

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?

Without an output schema, the description fully explains the return structure (opportunities array, partition check fields, fill check). It also mentions related tool 'polymarket_fill_risk' for custom sizing. Given the tool's complexity and no output schema, the description is complete and actionable.

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'. The description adds significant meaning: examples of valid inputs (slugs, URLs, seed questions), behavior differences between modes, and cross-event catching patterns. This goes beyond schema documentation.

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 between three modes: no-args trending scan, event-specific single-event scan, and topic cross-event scan, each with clear behavior.

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 explains when to use each mode (e.g., 'pass `event` for the strongest per-event partition_check', 'pass a seed question for cross-event scanning'). It also provides guidance on not trading when realizable_edge_pp ≤ 0. However, it does not explicitly compare to sibling tools like polymarket_edges or polymarket_fill_risk, though it mentions the latter 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 Emsc 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

A4/5.0
Disambiguation3/5

Multiple tools overlap: ask_pipeworx and ask_pipeworx_beta are currently identical, and the five prediction-market tools (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, polymarket_edge_tracker) cover adjacent tasks that require careful reading. However, descriptions are unusually explicit about when to prefer each, and non-overlapping domains (memory, subscriptions, earthquakes, npm) are clearly separated.

Naming Consistency4/5

All tool names are snake_case with a mostly verb-first pattern (ask_, compare_, discover_, generate_, list_, scan_, search_, validate_), making the surface predictable. Minor deviations like deep_research, entity_profile, and single-word verbs (remember, recall, forget) break the pattern slightly, but each family is internally consistent.

Tool Count2/5

33 tools exceeds the 25+ threshold for 'too many,' and several could be consolidated — ask_pipeworx_beta is redundant today, and the prediction-market suite could fold into 2-3 tools. The count reflects a genuinely wide data platform with meta-tools (discover_tools, suggest_questions, ask_pipeworx) already covering discovery, so the surface feels heavy for an agent to triage.

Completeness4/5

Core workflows are well covered: querying (ask_pipeworx, grounded, deep_research), research profiles (entity_profile, compare_entities, recent_changes), input resolution (resolve_entity), fact-checking (validate_claim), memory lifecycle, and subscription lifecycle all have complete loops. Minor gaps exist, notably no tool to fetch a pipeworx:// citation URI directly (search_within expects already-fetched text), and some one-off tools like generate_llms_txt and scan_dependency feel bolted on.

Resources