Skip to main content
Glama

The Committee

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?

The description richly discloses behaviors beyond the readOnly/openWorld/idempotent annotations. It details the computational checks (monotonicity, partition-sum), thresholds (>3pp, ≥0.30 Jaccard, >20% placeholder), the fill check against CLOB depth, and edge-case returns (null arb signal). 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 lengthy (~350 words) but well-structured with labeled segments (SEMANTIC ANCHOR, PARTITION FILTER, RESPONSE, FILL CHECK). It front-loads the core purpose in the first sentence. However, some redundancy exists in re-explaining the event/topic modes in detail after introducing them earlier. It could be slightly tightened, but it is organized and information-dense.

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 thoroughly explains return values: 'opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context)' and event-mode partition_check fields. It also covers edge cases like placeholder-filtered null signals and fill-check failure. For a tool this complex, the description is remarkably complete.

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?

Even though the schema already describes both parameters with 100% coverage, the description adds significant semantics: event mode 'walks child markets, checks date-axis/threshold-axis ordering AND computes the partition_check,' while topic mode 'searches related events, flattens markets, runs the comparator on the union.' It also provides concrete examples, enriching beyond 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 function: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It specifies the resource (Polymarket) and the action (find arbitrage), and distinguishes its three invocation modes (trending_scan, event, topic) from each other and from sibling tools like polymarket_fill_risk which is mentioned as the alternative for custom sizing.

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?

Provides explicit usage instructions: 'Call with NO args for a trending_scan...; pass event for...; or topic for...' It also states when to prefer event vs topic modes, and explicitly directs 'For custom sizing use polymarket_fill_risk.' The fill check section also tells the agent when not to trade. This is exemplary guidance.

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

All The Committee 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
Disambiguation3/5

The ask_pipeworx family creates real ambiguity: ask_pipeworx_beta explicitly states it currently matches ask_pipeworx exactly, leaving an agent no principled way to choose between them. discover_tools and suggest_questions also overlap as meta-tools for navigating the catalog, though the remaining tools (five polymarket_* tools, entity tools, subscription lifecycle) are well-delineated by their detailed cross-referenced descriptions.

Naming Consistency3/5

The set is uniformly snake_case with coherent subfamilies (ask_pipeworx*, polymarket_*, pipeworx_*, remember/recall/forget), but it mixes imperative verb_phrase names (validate_claim, resolve_entity, generate_llms_txt) with noun_phrase names (entity_profile, recent_changes, ai_visibility_check), and the_committee_convene breaks the pattern entirely with a full-sentence name. The inconsistency is stylistic rather than chaotic, so it stays readable.

Tool Count2/5

At 32 tools, the set exceeds the 25+ threshold for 'too many' and the breadth is not fully earned: ask_pipeworx_beta is self-admittedly redundant right now, and several tools feel bolted on from unrelated domains (the_committee_convene, generate_llms_txt, scan_dependency, ai_visibility_check). The core data-research and prediction-market scope would be tighter and more navigable at roughly 20-24 tools.

Completeness4/5

The primary domain — authoritative data lookup, entity research, and prediction-market analysis — is covered with no dead ends: query (ask_pipeworx, grounded, deep_research), profile (resolve_entity, entity_profile, compare_entities), track (recent_changes), verify (validate_claim), bet research (bet_research, polymarket_edges, arbitrage, fill_risk, kalshi_spread), subscriptions (subscribe/unsubscribe/list/recent_alerts), and memory (remember/recall/forget) form complete lifecycles. Minor gaps exist only at the periphery: no execution layer for prediction-market trades (research stops at fill-risk advice) and single-tool coverage for the npm/llms.txt/AI-visibility side-domains.

Resources