Skip to main content
Glama

Ulid

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

A4.9/5.0
Behavior5/5

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

The description adds significant behavioral context beyond the annotations (readOnlyHint, openWorldHint, idempotentHint). It details the partition check, semantic anchor with Jaccard similarity threshold, placeholder filtering, fill check with live CLOB depth, and conditions for not trading. This fully informs the user of the tool's internal logic and limitations. 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 front-loaded with the primary purpose and modes, but it is lengthy due to detailed explanations of partition checks, similarity thresholds, and fill risk. While every sentence adds value, the overall length could be trimmed slightly for quicker comprehension. The structure is logical and well-organized.

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 the complexity of the tool (multiple modes, partition checks, fill risk, filters), the description is remarkably complete. It covers usage, parameter details, response structure (opportunities, partition_check, fill details), conditions for valid signals, and references to related tools. Despite the lack of an output schema, the description sufficiently explains what the tool returns.

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 coverage is 100%, but the description enriches both parameters significantly. For 'event', it clarifies acceptable formats (slugs or URLs) and mode behavior. For 'topic', it explains how the seed question is used and the cross-event scanning process. This goes well beyond the schema descriptions, providing practical usage insights.

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's purpose: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It distinguishes itself from sibling tools like polymarket_fill_risk by specifying unique methods and modes, such as trending_scan, event, and topic. The verb 'find' and resource 'arbitrage opportunities' are specific and actionable.

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?

The description provides explicit guidance on when to use each mode: call with NO args for trending scan, pass event for a specific market, or topic for cross-event scanning. It recommends event mode for specific markets and explains that cross-event mode catches patterns missed by single-event scanning. Also, it directs users to polymarket_fill_risk for custom sizing, offering clear alternatives.

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

All Ulid 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

Several tool clusters overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all serve as query entry points (with ask_pipeworx_beta explicitly identical to ask_pipeworx right now); polymarket_edges, polymarket_edge_tracker, polymarket_arbitrage, polymarket_fill_risk, polymarket_kalshi_spread, and bet_research form a dense prediction-market suite; ai_visibility_check and scan_competitor_ai_presence are single vs. multi variants. An agent would frequently struggle to pick the right tool without reading long descriptions.

Naming Consistency4/5

Most tools follow a clean snake_case convention and are mostly verb_noun (generate_ulid, parse_ulid, list_subscriptions, resolve_entity, validate_claim, compare_entities), making the set predictable. Minor deviations exist (entity_profile, deep_research, bet_research, ask_pipeworx_beta) but they are still readable and don't break the overall pattern.

Tool Count2/5

33 tools is well above the 25-tool threshold for a heavy surface, and the server name 'Ulid' suggests a tiny scope that wildly mismatches the actual content. While the real domain (Pipeworx data + prediction markets) is broad, the set bundles many subdomains into one server, making navigation and selection costly.

Completeness4/5

For the actual apparent domain—structured data research, entity lookups, verification, prediction-market analysis, memory, and subscriptions—coverage is strong: query, grounded query, deep research, entity profiles, comparisons, resolution, validation, discovery, alerts, and memory tools are all present. ULID functionality is minimal but sufficient (generate + parse). Minor gaps exist (e.g., no direct single-source browser beyond discover_tools) but agents can work around them.

Resources