Skip to main content
Glama

Dostuff

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 indicate read-only, idempotent, open-world, non-destructive. Description adds significant behavioral detail: scanning top 200 markets, partition_check logic (sum of YES prices ~1, gap >3pp triggers signals), semantic anchor (Jaccard similarity >=0.30), partition filter (placeholder slugs, >20% placeholder returns null). Discloses fill check and what response contains. 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 lengthy (multiple paragraphs) but well-structured: starts with summary, then explains each mode, details on semantic anchor and partition filter, response format, and fill check. Every sentence adds value given complexity. Slightly verbose but justified; no wasted words.

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 documents the response structure (opportunities array with gap_pp, suggested_trade, reasoning, monotonicity context; partition_check with sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade; fill check fields). Covers multiple modes, edge cases (placeholder filtering), and provides warnings (do not trade if realizable_edge_pp <= 0). Fully informed for an AI agent.

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 descriptions already cover both parameters (event slug/topic), but the description adds essential context: explains event slug format (accepts full URLs), topic as seed question, and the behavioral difference between modes. It also clarifies that passing no arguments triggers a default trending scan. Schema coverage is 100%, but description goes beyond to fully explain 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?

The description clearly states the tool finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes three modes: no args (trending_scan), event (single-market), and topic (cross-event). This specificity differentiates it 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 Guidelines5/5

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

Explicitly explains when to use each parameter: no args for trending scan, event for a specific market with slug/URL, topic for cross-event scanning. Provides recommendations ('event recommended') and warns about fill check with realizable_edge_pp <= 0 meaning 'do not trade'. References sibling tool 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 Dostuff 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

The set contains near-duplicate tools (ask_pipeworx_beta explicitly 'currently matches ask_pipeworx exactly') and a dense family of six polymarket_* tools whose boundaries are subtle, plus overlapping onboarding tools in discover_tools and suggest_questions. Detailed descriptions mitigate some confusion, but several tools are difficult to tell apart without reading their full text.

Naming Consistency3/5

All names are lowercase snake_case and readable, with consistent prefix families (ask_pipeworx, polymarket_, pipeworx_), but the overall structure is mixed: bare verbs (remember, forget, subscribe), adjective+noun names (recent_alerts, recent_changes), and noun+noun domain tags (polymarket_edges, entity_profile) rather than a uniform verb_noun pattern.

Tool Count2/5

At 33 tools the set exceeds the 25-tool threshold and feels heavy, carrying an experimental duplicate of ask_pipeworx and a six-tool polymarket family that could plausibly be consolidated. The breadth reflects several unrelated domains bundled into one server rather than a focused scope.

Completeness3/5

The data-research core (ask, grounded, deep_research, profiles, comparisons, claim validation, entity resolution) and the prediction-market analysis suite are thoroughly covered, and memory plus subscription lifecycles are complete. However, the events domain the server is named for is thin (only events + metros), and the overall set lacks a single coherent purpose against which completeness can be cleanly judged.

Resources