Skip to main content
Glama

Gdacs

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?

Even though annotations already include readOnlyHint, openWorldHint, and idempotentHint, the description adds crucial behavioral details beyond them, such as the FILL CHECK mechanism, the meaning of realizable_edge_pp <= 0, the PARTITION FILTER's placeholder logic, and the SEMANTIC ANCHOR's Jaccard similarity threshold. This explains side effects and edge-case behavior far beyond structured hints.

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 long but every sentence earns its place. It is logically structured with labeled sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and front-loaded with the core purpose and mode overview. The density is justified by the tool's complexity, and it avoids redundancy.

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 tool with no output schema, the description thoroughly explains response shapes (opportunities[] with fields, partition_check object), caveats (fill check, placeholders), and failure modes (realizable_edge_pp <= 0). It covers both parameter modes and operational edge cases, making it complete for an agent to invoke 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%, but the description greatly expands on the bare schema. For 'event', it explains slug format, accepts full URLs, and describes how it walks child markets. For 'topic', it defines a 'seed question' and explains cross-event flattening and union checks. This adds meaning far beyond the schema's one-line property descriptions.

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.' It clearly differentiates from siblings by detailing three modes (no args, event, topic) and explicitly references polymarket_fill_risk for custom sizing, distinguishing it from polymarket_edges and similar tools.

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 a trending_scan...' and says 'event (recommended for a specific market)' vs 'topic (for cross-event scanning)'. It also names an alternative tool for custom sizing and explains cross-event mode's unique capability, giving clear situational direction.

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

All Gdacs 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

A3.5/5.0
Disambiguation4/5

Most tools have clear, distinct purposes, but the three ask_pipeworx variants (especially ask_pipeworx_beta, identical to ask_pipeworx) and the six Polymarket tools overlap conceptually and could cause misselection. Detailed descriptions largely compensate, but the boundaries between some meta-tools (e.g., ask_pipeworx vs deep_research vs bet_research) require careful reading.

Naming Consistency3/5

All names are snake_case, but conventions are mixed: verb-first (ask_pipeworx, compare_entities, discover_tools), noun-first compounds (entity_profile, polymarket_arbitrage), and single-word nouns (event, events, rss). The pattern is predictable for common actions but inconsistent across the set, making it harder to guess names for related tasks.

Tool Count2/5

At 35 tools, the count is heavy and the server named 'Gdacs' includes many unrelated tools (Polymarket, npm scanning, AI visibility), indicating scope creep. Several tools could be consolidated (e.g., the ask_pipeworx family and multiple pattern-market scanners), and the breadth dilutes the disaster-alerting focus implied by the server name.

Completeness4/5

The surface covers core workflows: data querying (ask/research/validate), entity profiling, prediction-market analysis (arbitrage/edges/fill risk), and subscription management (create/list/cancel). Minor gaps exist, such as no direct fetch tool for a specific Pipeworx pack and limited GDACS event management (only read operations), but these are workable with the provided meta-tools.

Resources