Skip to main content
Glama

Data Cambridge

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

A5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds rich behavioral context: scanning process, Jaccard similarity threshold, placeholder filtering, fill check against live CLOB depth, and response structure. No contradictions.

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?

Long but well-structured with clear sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). Front-loaded with purpose and modes. Every sentence adds necessary detail for correct tool invocation and interpretation of results.

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 fully explains return values: opportunities[] with fields and partition_check for event mode. Covers edge cases like skipped_low_similarity and placeholder filtering. Complete for a complex arbitrage detection tool.

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?

Input schema has 100% coverage for both parameters. The description adds significant meaning beyond the schema: explains event mode slugs, topic mode seed questions, and notes that full Polymarket URLs are accepted for the event parameter. Provides concrete examples.

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?

Clearly states it finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. Distinguishes itself from sibling tools like polymarket_edges and polymarket_fill_risk by explaining its role and referring to polymarket_fill_risk for custom sizing.

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 describes when to use no args (trending scan), event mode (specific market), and topic mode (cross-event scan). Provides rationale for each mode and warns against trading when fill check shows realizable edge ≤ 0. Also directs to polymarket_fill_risk 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 Data Cambridge 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

A3.9/5.0
Disambiguation3/5

Most clusters have clear roles, and the detailed routing guidance separates ask_pipeworx from deep_research and grounded mode. However, three ask_pipeworx variants (one currently identical to stable), plus overlapping opportunity-discovery tools (polymarket_edges vs bet_research) and discovery/onboarding tools (discover_tools vs suggest_questions), leave several boundary cases where an agent could select the wrong tool.

Naming Consistency3/5

Many tools group under readable prefixes (ask_pipeworx, cambridge_, polymarket_, pipeworx_) and are mostly snake_case. But the set mixes bare verbs (remember, recall, forget), verb_noun actions (resolve_entity, validate_claim), and noun-phrase names (entity_profile, recent_changes, polymarket_fill_risk), so no single convention predicts the full API.

Tool Count2/5

34 tools is well into the 'too many' band, and the count is inflated by a kitchen-sink mix of data querying, prediction-market analysis, memory, subscriptions, feedback, llms.txt generation, and npm scanning. The server name 'Data Cambridge' suggests a narrow local-data scope, which makes the sprawl look even less appropriate.

Completeness3/5

Individual verticals are fairly complete: query/grounded/beta router levels, entity resolution/profile/compare/change, prediction-market discovery through fill-risk, and full memory and subscription CRUD. The major gap is discover_tools, which returns tools promoted as ready to call directly but no generic invocation tool is exposed, so the agent must route back through ask_pipeworx.

Resources