Skip to main content
Glama

Worms

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=true and idempotentHint=true. The description goes far beyond by detailing the internal checks (monotonicity, partition sum, semantic anchor, placeholder filter, fill check against CLOB depth) and the exact conditions for a valid arbitrage signal. It discloses the real-world constraint that a trade should not be executed if the edge exists only at last-trade.

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?

The description is front-loaded with the core purpose and then organized into clear sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). Every sentence provides necessary information for correct tool use; there is no fluff. Despite its length, it is well-structured and efficiently conveys complex logic.

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?

For a complex arbitrage detection tool with no output schema, the description fully covers input modes, internal algorithms, response structure (opportunities[], partition_check, fill_check details), and even cross-references polymarket_fill_risk for custom sizing. It addresses limitations (placeholder filters, similarity thresholds) and provides complete guidance for an AI agent to use the tool correctly.

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?

The input schema has 100% description coverage for both parameters. The description adds significant context beyond the schema: it explains that event expects a Polymarket event slug or full URL, and topic expects a seed question. It gives concrete examples (e.g., 'fed-decision-may-2026', 'Strait of Hormuz traffic returns to normal') and clarifies the behavior of each mode, making parameter meaning much richer.

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 opens with a clear verb+resource: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It immediately distinguishes the tool's purpose and its two main modes (event/topic), providing a specific, actionable definition that differentiates it from sibling tools like polymarket_edges or 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?

Explicit guidance is given for when to use each parameter: 'Call with NO args for a trending_scan... pass event for the strongest per-event partition_check, or topic for a themed cross-event scan.' It recommends event mode for specific markets and warns against trading when the fill check shows no realizable edge. This covers when, when-not, and alternatives within the tool.

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

All Worms 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

A3.6/5.0
Disambiguation2/5

Several tools have functionally overlapping purposes, most notably ask_pipeworx and ask_pipeworx_beta, which currently behave identically. The many prediction-market tools are each distinct but still leave boundaries that require careful reading, and the query/research tools (ask_pipeworx, deep_research, potentially validate_claim) have an ease of being confused. Fine verbal descriptions reduce but do not eliminate the ambiguity for an agent.

Naming Consistency3/5

All names are lowercase snake_case and many follow a verb_noun pattern, such as resolve_entity, get_classification, and list_subscriptions. However, the set is inconsistent overall: it mixes single verbs (remember, forget, subscribe), noun-style names (entity_profile, recent_alerts), and several prefixed families (pipeworx_*, polymarket_*). It's readable but not a coherent, uniformly applied convention throughout.

Tool Count2/5

34 tools in one server is well beyond the generally well-scoped 3–15 range. The server appears to bundle several unrelated domains together—WoRMS taxonomy, Pipeworx data research, Polymarket analysis, memory utilities, and subscriptions—creating avoidable cognitive load and making selection more difficult. Splitting into targeted servers would greatly improve the interface.

Completeness2/5

The server is named 'Worms' and includes a WoRMS taxonomy subdomain, but that subdomain only supports searching, classification, and common names—the rest of the marine taxonomy surface is missing (e.g., direct AphiaID record lookup, distributions, synonyms, hierarchical children). The remainder of the tools serve an entirely different data-research purpose, so the server is incomplete relative to its name AND the bundled extra domains add confusion rather than a coherent cohesive coverage.

Resources