Skip to main content
Glama

Arcgis Longview

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

A5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, but the description adds rich behavioral detail: threshold >3pp for signals, Jaccard similarity ≥0.30 for semantic pairing, placeholder filtering (20% threshold), and the fill check against live CLOB depth. This goes well beyond the annotations and provides critical context for interpreting results.

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?

While long, the description is densely informative and well-structured with clear sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). Every sentence adds value—no redundancy or filler. Important details are front-loaded, and the formatting makes complex behavior easy to scan.

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 tool with no output schema and only two optional parameters, the description covers all necessary context: response structure, thresholds, failure modes, and caveats. It also references sibling tools to direct users for related tasks, making it effectively self-contained for an AI agent.

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 descriptions cover the basic purpose of each parameter, but the description adds substantial semantics: event mode walks child markets and checks ordering plus partition_check, while topic mode searches related events and flattens markets. It also provides concrete examples of valid inputs (e.g., 'fed-decision-may-2026', 'Strait of Hormuz traffic returns to normal').

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: finding arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes two modes (event and topic) and a default trending scan, making it specific and 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 on when to use each mode: event for a specific market, topic for cross-event scanning, and no args for a trending scan. It also references an alternative tool for custom sizing ('For custom sizing use polymarket_fill_risk') and warns against trading when realizable edge is non-positive.

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

All Arcgis Longview 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

Descriptions are unusually explicit about when to use each tool (single lookup vs grounded vs deep research), but the set still contains several genuinely overlapping tools: ask_pipeworx_beta is explicitly identical to ask_pipeworx, scan_competitor_ai_presence wraps ai_visibility, and six polymarket_* tools share the same 'edge/arbitrage' conceptual space. An agent can usually pick the right tool but faces real ambiguity in several clusters.

Naming Consistency4/5

Names are uniformly snake_case and readable, and there are coherent prefix families (ask_pipeworx_*, polymarket_*, pipeworx_*). However the verb placement is inconsistent: verb_noun (ask_pipeworx, validate_claim, discover_tools) coexists with noun-first names (recent_changes, entity_compare, layer_info, polymarket_edges), and bet_research sits outside the polymarket_* family despite being a prediction-market tool.

Tool Count2/5

34 tools is well past the 'feels heavy' threshold, and more importantly the set mixes what looks like three different servers: a tiny ArcGIS/Longview GIS slice (layer_info, query_layer, search_datasets), a massive general-purpose data-research platform from Pipeworx, and a Polymarket prediction-market toolkit. Most tools earn their place for the platform, but far too few belong to the named domain.

Completeness4/5

The research surface is remarkably complete: a router, grounded and beta variants, deep multi-source research, claim verification, entity/profile/change resolution, discovery and suggestion helpers, memory (remember/recall/forget), subscriptions (subscribe/unsubscribe/recent_alerts), and feedback — no obvious lifecycle dead ends. Minute gaps exist on the GIS side (no dataset editing, no metadata browsing, no named export/view ops) and a few nooks like screen- leisure tools have no progress/status endpoints, but these are workaroundable.

Resources