Skip to main content
Glama

Cpsc

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?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description enriches this with internal logic: Jaccard similarity threshold (≥0.30), placeholder filtering (skipped_low_similarity, placeholders_filtered), and the fill-check behavior against live CLOB depth. It also reveals the '>3pp emit a BUY/SELL EVERY LEG signal' rule, which is significant behavioral context not derivable from 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 long but well-structured: a one-sentence purpose, followed by clearly labeled mode sections (event, topic), semantic anchor, partition filter, response format, and fill check. It front-loads the primary verb and resource, and each paragraph adds distinct value. However, some illustrative examples (e.g., 'Powell-Fed-Pause being paired with Powell-DOJ-probe') are arguably expendable, making it slightly less concise than ideal.

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?

With no output schema, the description compensates by explaining the response structure ('opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context)') and the partition_check details. It covers both modes, filters, fill-check logic, and fallback to polymarket_fill_risk. Given the tool's complexity, the description leaves no significant gaps for an agent to invoke and interpret results 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?

Schema coverage is 100% with descriptions for both 'event' and 'topic', but the description adds critical semantics beyond the schema: it explains mode-specific behavior, provides concrete example slugs and seed questions, and clarifies that 'event' walks child markets while 'topic' flattens across events. This enables correct parameter selection beyond what the schema properties alone convey.

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 specific verb and resource: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' This clearly states the tool's function and is distinct from sibling tools like polymarket_edges (tracks edges) and polymarket_fill_risk (sizing), with an explicit cross-reference to fill_risk for sizing. The purpose is unambiguous and well-scoped.

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 when-to-use guidance: 'Call with NO args for a trending_scan', 'event (recommended for a specific market)', and 'topic (for cross-event scanning)'. It also names an alternative tool ('For custom sizing use polymarket_fill_risk') and clarifies when the fill check is necessary ('when the partition signal fires... do not trade it'). This fully addresses usage context and exclusions.

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

All Cpsc 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 tools are organized into clearly differentiated families (ask_pipeworx vs ask_pipeworx_grounded, polymarket_edges vs polymarket_arbitrage), but there are some genuinely ambiguous pairs: ask_pipeworx_beta is currently identical to ask_pipeworx, and search_recalls/recent_recalls, ai_visibility_check/scan_competitor_ai_presence, and bet_research/polymarket_edges all require careful reading to avoid misselection.

Naming Consistency3/5

The set is consistently lowercase snake_case and contains strong families like ask_pipeworx*, polymarket_*, recent_*, and search_*. However, the naming pattern is mixed: imperative verbs (recall, forget, subscribe), noun phrases (entity_profile, recent_changes, pipeworx_trending), and action prefixes (scan_, generate_, validate_) all coexist, making the overall convention less predictable than a uniform verb_noun scheme.

Tool Count2/5

With 33 tools, the server exceeds the healthy range and spreads across many side domains: data research, prediction markets, memory, subscriptions, npm dependency checks, llms.txt generation, and AI visibility audits. No individual tool feels pointless, but the overall surface is sprawling rather than tightly curated for a single purpose.

Completeness4/5

The core research workflow is well covered: querying, grounded verification, entity resolution, profiles, comparisons, recent changes, claim validation, deep research, memory, and subscriptions. Minor gaps exist—there is no direct reader for pipeworx:// citation URIs, no tool to update or edit a stored memory, and subscriptions can be created/cancelled but not modified—but agents can work around these.

Resources