Skip to main content
Glama

words

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. Added

TDQS

A5/5.0
Behavior5/5

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

Given annotations already signal read-only, idempotent, non-destructive behavior, the description adds meaningful operational context: partition thresholds (>3pp), placeholder filters (20%), semantic anchor similarity (≥0.30 Jaccard), and the fill-check logic against live CLOB depth. It also warns when not to trade (realizable_edge_pp ≤ 0). 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 long but every sentence carries operational weight—covering detection modes, filters, thresholds, output shape, and fill-risk caveats. It is well-organized into logical segments (modes, semantic anchor, partition filter, response, fill check) and front-loaded with the core purpose.

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?

For a complex tool with no output schema, the description compensates thoroughly by enumerating response fields (gap_pp, suggested_trade, reasoning, monotonicity context, partition_check) and explaining the fill-check pipeline. All critical user decisions (which mode, how to interpret deviations, when to avoid trading) are covered.

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?

Although the schema already describes both parameters (event and topic) with examples, the description goes further by explaining the no-args default (trending_scan), providing detailed slug examples ('fed-decision-may-2026'), and clarifying that full URLs are accepted. It also connected each parameter to the detection mode and explained the trade-offs.

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: 'Find arbitrage opportunities on Polymarket' and immediately distinguishes the detection methods (monotonicity violations, partition-sum checks) from sibling tools like polymarket_edges and polymarket_fill_risk. It clearly defines the tool's unique capability and scope.

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?

Explicit guidance is provided for every mode: no args for trending_scan, event slug for single-event, and topic for cross-event scanning. It includes recommendations when to use each and points users to polymarket_fill_risk for custom sizing, effectively explaining alternatives.

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

All words 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

A3.7/5.0
Disambiguation2/5

Several tools overlap heavily: ask_pipeworx_beta is currently identical to ask_pipeworx, and find_related with syn/rhy options duplicates find_synonyms and find_rhymes. The six Polymarket tools and four entity-research tools also have fuzzy boundaries, so agents will struggle to reliably pick the right one.

Naming Consistency2/5

Conventions are mixed: most tools follow verb_noun (ask_, find_, compare_, validate_) but several are bare nouns or noun phrases (entity_profile, recent_alertes, recent_changes) and others are bare verbs (remember, forget, subscribe, unsubscribe). The server name 'words' matches only five of 36 tools, adding further confusion about what to expect here.

Tool Count2/5

36 tools is well into the heavy range, and the set bundles word lookups, a universal data router, six Polymarket tools, memory, subscriptions, and meta-utilities under one server. Many of these would be better split into dedicated, purpose-scoped servers.

Completeness4/5

For the dominant data-research and prediction-market scope, the surface is strong: grounded lookups, deep reseach, entity profiles, compareions, change feeds, claim verification, edge scanners, fill-risk checks, subscriptions, and memory are all covered. Minor gaps exist: taking 'words' literally there is no defintion or spelling tool, and there is no generic open-web search, but as a data-research toolkit it is quite complete.

Resources