Skip to main content
Glama

Science Feeds

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

A4.8/5.0
Behavior5/5

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint false), the description discloses internal logic (semantic anchor, partition filter, fill check against CLOB depth), response structure, and limitations (skipped_low_similarity, placeholder filtering). No contradictions 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 thorough and well-organized, starting with overall purpose, then detailing each mode, followed by additional checks and response. While lengthy, every sentence adds value; could be slightly more concise but remains clear.

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 (arbitrage detection, multiple modes, no output schema), the description covers all necessary aspects: parameters, modes, internal checks, response structure, and fill risk. It provides sufficient information for an agent to understand and use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers parameters 100%, but the description adds significant value by explaining the meaning of event slugs and topic seed questions, providing examples, and detailing behavioral differences between modes. Accepting full URLs is also noted.

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 finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes itself from siblings like polymarket_edges and polymarket_fill_risk by specifying its unique methodology and also mentions alternative tools 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 guidance on when to use each mode (no args for trending scan, event for specific market, topic for cross-event scan) and recommends event mode for specific markets. It also explains when not to trade (if realizable_edge_pp <= 0) and directs to polymarket_fill_risk for custom sizing.

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

All Science Feeds 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
Disambiguation2/5

ask_pipeworx, ask_pipeworx_beta (currently identical in behavior), and ask_pipeworx_grounded overlap heavily, and the six-tool Polymarket cluster (edges, arbitrage, fill_risk, edge_tracker, kalshi_spread, bet_research) requires careful reading to distinguish. Descriptions are detailed, but several tools present real selection ambiguity.

Naming Consistency4/5

Nearly all tools use snake_case with a mostly verb-first or resource-first pattern (ask_, list_, fetch_, read_, subscribe, validate_claim). Minor deviations like entity_profile and recent_changes break the verb-noun pattern slightly, but the overall naming is predictable.

Tool Count2/5

34 tools is excessive for the 'Science Feeds' name, which implies a narrow feed-reading service; only 3 tools actually relate to feeds. The rest form a broad Pipeworx grab bag (memory, npm scanning, AI visibility, prediction markets, feedback), making the set feel unfocused and overweight.

Completeness4/5

For the broad query/research domain the descriptions actually establish, coverage is strong: discovery, single lookups, grounded/refusal-safe answers, deep research, entity resolution, comparison, change feeds, claim validation, subscriptions, memory, and feedback are all present. The literal science-feed surface is thin, but the toolkit as a whole has few dead ends.

Resources