Skip to main content
Glama

usgswater

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?

The description discloses key behaviors that go beyond the readOnlyHint/idempotentHint annotations, such as the partition filter for placeholder slugs, the semantic anchor threshold (Jaccard ≥ 0.30), and the fill-check logic explaining when a signal is not tradeable. It also states the response structure, providing full transparency about what the tool returns. 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-organized using CAPS-labeled sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and a clear front-loaded summary sentence. Every sentence contributes new information, and the length is justified by the tool's complexity.

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 lacking an output schema, the description explicitly lists the response fields (opportunities[], partition_check{}, fill check details), covering what an agent needs to understand the return value. It also explains the edge case of realizable_edge_pp ≤ 0 and directs to polymarket_fill_risk for custom sizing, making the tool self-contained.

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?

Both parameters (event and topic) already have detailed schema descriptions covering 100% of the parameters. The description substantially enriches the semantics by explaining exactly what each mode does—e.g., 'walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check' for event, and the cross-event search behavior for topic. It also adds the semantic anchor and partition filter context that are not present in the schema.

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 with a specific verb and resource: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It further distinguishes the two input modes (event and topic) and the no-arg trending scan, making it distinct 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?

The description provides explicit guidance for when to use each mode: no args for a trending scan, `event` for a specific market, and `topic` for cross-event scanning. It also notes limitations ('Cross-event mode catches ... patterns that single-event misses') and points to an alternative tool for custom sizing ('For custom sizing use polymarket_fill_risk').

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

All usgswater 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

Several tools overlap: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all serve as query routers, with the beta variant currently identical to the stable one. However, most other tools have clearly distinct purposes (memory, subscriptions, prediction market analytics), and the detailed descriptions help differentiate them.

Naming Consistency4/5

All tool names use snake_case and are descriptive, with consistent domain prefixes like pipeworx_ for meta tools and polymarket_ for prediction markets. Some names mix noun-phrase and verb-noun patterns (e.g., ai_visibility_check vs. resolve_entity), but the overall style is predictable and readable.

Tool Count2/5

With 31 tools, the server exceeds the 25-tool threshold for a coherent set. While the broad scope (data querying, prediction markets, memory, subscriptions, AI visibility) justifies many tools, the sheer number creates cognitive load and makes selection harder for agents.

Completeness4/5

The tool surface is quite comprehensive for its domains: querying has ask_pipeworx, grounded answer, deep research, entity profiles, comparisons, and claim validation; prediction markets have research, arbitrage, edge tracking, and fill risk; memory and subscription lifecycles are covered. Minor gaps exist (e.g., no subscription update) but are workable.

Resources