Skip to main content
Glama

Data Denver

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 (readOnlyHint, openWorldHint, idempotentHint, destructiveHint false) establish safety and idempotency. The description enriches this with detailed behavior: semantic similarity thresholds, placeholder filtering, partition sum checks, and fill check logic. No contradictions exist; the description adds value beyond the 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 fairly long but well-structured, starting with a summary, then breaking into mode details, filters, response format, and fill check. While comprehensive, a slight reduction (e.g., moving some details to a separate note) could improve conciseness without losing critical information.

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?

Given no output schema, the description thoroughly explains the response structure, including fields like gap_pp, suggested_trade, reasoning, and partition_check in event mode. It covers what happens with each input mode, edge cases (e.g., placeholder filtering), and even warns when the trade is not realizable. The tool's interaction with a sibling tool (polymarket_fill_risk) is noted, ensuring the agent has full context.

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 input schema covers both parameters 100%, the description adds significant meaning: it explains the purpose of each parameter, provides real-world usage examples, and details how each mode operates. This helps the agent understand the semantic impact of choosing event vs. topic beyond the schema descriptions.

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 verb 'Find arbitrage opportunities', the resource 'on Polymarket', and the methods 'via monotonicity violations + partition-sum checks'. It distinguishes three distinct modes (no args, event, topic) and uses specific examples, making the purpose unambiguous and well-differentiated from sibling tools.

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 each mode: 'Call with NO args for a trending_scan', 'event (recommended for a specific market)', and 'topic (for cross-event scanning)'. It includes usage examples, conditions for when not to trade, and references a sibling tool for custom sizing, giving clear when-to-use and when-not-to-use advice.

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

All Data Denver 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

Tools are richly described with clear use-cases, but several clusters overlap: ask_pipeworx/ask_pipeworx_beta/ask_pipeworx_grounded/deep_research are all question-routing tools with similar names, and the five polymarket_* tools cover adjacent prediction-market analysis. An agent could easily pick the wrong one without reading the full descriptions.

Naming Consistency4/5

All names are snake_case and mostly follow a verb_noun or domain_noun pattern (compare_entities, resolve_entity, denver_query, polymarket_edges, pipeworx_trending). There are minor deviations like single verbs (remember, forget), adjective-first names (recent_alerts, deep_research), and domain-prefixed groups, but the overall style is predictable and readable.

Tool Count2/5

34 tools is a large surface for one server, pushing beyond the 25+ threshold where agents struggle to choose. While the platform is genuinely multi-domain (data lookup, prediction markets, Denver open data, memory, subscriptions, npm checks, llms.txt generation), several niche clusters like the 5-tool Polymarket suite and 3-tool memory trio inflate the count.

Completeness4/5

The server covers its domain well: general querying, grounded verification, deep research, entity resolution, company profiling, change feeds, subscription lifecycle (subscribe/list/unsubscribe/alerts), memory lifecycle (remember/recall/forget), and discovery (discover_tools, suggest_questions). Minor gaps exist—such as no direct browsing of all Pipeworx sources—but agents can work around them.

Resources