Skip to main content
Glama

Arcgis Pittsburgh

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?

Annotations only declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive; the description adds extensive behavioral context: it walks child markets, computes partition sums, filters placeholder slugs, surfaces skipped_low_similarity, and describes what the response contains. It even discloses that a theoretical edge may not be realizable at the book depth, which goes far beyond what annotations imply. 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 long but dense and well-organized with clear section labels (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and front-loaded purpose. Every sentence adds operational detail, from Jaccard threshold to placeholder fraction, without filler. The structure mirrors the tool's rich internal logic, making it 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?

Given the tool's complexity and the absence of an output schema, the description is fully self-sufficient: it explains the two modes, the response fields (opportunities[], partition_check, gap_pp, suggested_trade), the fill-check mechanism, and edge cases like realizable_edge_pp. It also covers the conditions under which no signal is returned (placeholder fraction >20%), making the tool's behavior predictable in all advertised scenarios.

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?

Although schema coverage is 100%, the description greatly enriches both parameters: it explains how 'event' triggers per-event partition/ordering checks with example slugs, while 'topic' enables a cross-event flattening process with a seed question. It also clarifies the relationship between parameters (they are alternative modes, not combinable), which the schema alone does not 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 phrase: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks,' identifying both the action and the resource. It explicitly distinguishes this tool from siblings like polymarket_edges and polymarket_fill_risk by detailing its unique dual-mode logic (event vs topic) and its focus on structural arbitrage rather than generic edge detection.

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 instructions: call with no args for trending scan, pass 'event' for per-event checks, or 'topic' for cross-event scanning. It also points to a specific alternative ('For custom sizing use polymarket_fill_risk') and includes a strong negative directive ('do not trade it' when realizable_edge_pp ≤ 0), leaving no ambiguity about usage context.

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

All Arcgis Pittsburgh 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

B3.4/5.0
Disambiguation2/5

Several near-duplicate tool clusters exist: ask_pipeworx, ask_pipeworx_beta (explicitly identical right now), and ask_pipeworx_grounded overlap heavily, as do polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, and polymarket_kalshi_spread. The three ArcGIS tools (search_datasets, layer_info, query_layer) are distinct, but their purpose is drowned out by the unrelated Pipeworx data tools.

Naming Consistency2/5

Most names use snake_case, but the pattern is inconsistent: some are verb_noun (ask_pipeworx, search_datasets, resolve_entity), some are noun_noun (layer_info, entity_profile, pipeworx_feedback), and some are adjective_noun (recent_alerts, recent_changes). Verbs are also inconsistent across similar actions (scan_ vs check_ vs compare_, and three different polymarket_ verbs plus a bare bet_research).

Tool Count1/5

34 tools is already heavy, but the server is named Arcgis Pittsburgh and only 3 of the 34 tools relate to Pittsburgh GIS data; the other 31 belong to unrelated domains (Pipeworx data lookup, prediction markets, memory, npm auditing). This is an extreme scope mismatch — the tool count is far too high for the stated purpose and mostly irrelevant noise.

Completeness2/5

For the ArcGIS Pittsburgh domain, the surface has basic read coverage (search datasets, inspect layer schema, query records) but no update/delete/write operations and no geospatial analysis tools, which are significant gaps for a GIS server. The broader tool set is a grab bag of research, prediction-market, and memory features that don't form a coherent lifecycle for any single domain, so completeness cannot be assessed as a unified surface.

Resources