Skip to main content
Glama

Data Iledefrance

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. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds substantial behavioral context: monotonicity violation checks, partition sum checks, Jaccard similarity threshold (0.30), placeholder filtering, fill check logic against CLOB depth, and realizable edge computation. 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 front-loaded with the core purpose and modes. It then dives into technical details (similarity, partition filter, fill check). While informative, it is somewhat long (9 sentences) and could be tightened, but the structure is logical with clear sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK).

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?

No output schema, so the description must cover return values. It adequately describes the response structure: opportunities array with fields (gap_pp, suggested_trade, reasoning, monotonicity violation context), partition_check object in event mode, and fill check details. However, it could be clearer about the exact format of response objects and potential edge cases. Overall, sufficient for an agent to understand what to expect.

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?

Schema coverage is 100% (both parameters documented). The description adds valuable meaning beyond schema: provides example values for event slug and topic, explains how topic triggers cross-event search, and clarifies the partition check behavior. Slightly verbose but adds context for both parameters.

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 states the tool finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It explicitly distinguishes three modes (no args, event, topic), each with clear behavior and context. This clearly differentiates it from sibling tools like polymarket_edges.

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?

Provides explicit guidance: no args for trending scan of top 200 markets; event for specific market with partition check; topic for cross-event scanning. Recommends event mode for specific markets and explains cross-event mode catches patterns single-event misses. Explicitly mentions when not to use (e.g., 'do not trade it' when fill check shows zero realizable edge). Alternatives like polymarket_fill_risk are referenced.

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

All Data Iledefrance 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

A3.5/5.0
Disambiguation2/5

Many tools have overlapping purposes, e.g., multiple ask/tools for querying (ask_pipeworx, ask_pipeworx_grounded, deep_research) and multiple company analysis tools (entity_profile, compare_entities, recent_changes). The prediction market tools (bet_research, polymarket_arbitrage, etc.) further blur distinctions. Agents would frequently select the wrong tool.

Naming Consistency2/5

Naming conventions are inconsistent: snake_case (ask_pipeworx, dataset_info), camelCase (ai_visibility_check, scan_competitor_ai_presence), and phrases (pipeworx_feedback, polymarket_arbitrage). No pattern emerges, making tool discovery harder.

Tool Count2/5

33 tools is excessive for a server ostensibly about Île-de-France Open Data. Only 3 tools (dataset_info, query, search_datasets) relate to that domain, while the rest are a general-purpose data agent with many disjoint capabilities. The count feels bloated and unfocused.

Completeness2/5

For the declared purpose (Île-de-France data), the tool set is missing CRUD operations (no create/update/delete). For the actual general data use, there are gaps like missing person entity resolution, data visualization, and file handling. The deep_research tool requires an account, creating a barrier.

Resources