Skip to main content
Glama

Watchmode

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?

Annotations already declare readOnlyHint=true and idempotentHint=true; description adds rich behavioral context: it performs scans, checks fill depth, filters placeholders, and explains semantic anchors. No contradictions.

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 but well-structured with clear sections for each mode and response details. Every sentence contributes value, though some repetition exists (e.g., fill check explained twice).

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?

Despite no output schema, the description fully explains the response structure (opportunities[], partition_check, fill check), failure cases (skipped_low_similarity, placeholders), and trading guidance, making it self-contained.

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 coverage is 100% with detailed descriptions; the description adds contextual examples (slugs, seed questions) and explains the effect of each mode, slightly enhancing meaning 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 identifies the tool's purpose: finding arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes itself from sibling tools by naming specific modes (event, topic) and referencing polymarket_fill_risk 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?

Explicitly states when to use each mode ('event recommended for a specific market', 'topic for cross-event scanning'), when not to trade (realizable_edge_pp ≤ 0), and provides alternatives (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 Watchmode 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
Disambiguation2/5

The server packs in three near-identical question-answering entry points (ask_pipeworx, ask_pipeworx_beta which explicitly states it 'currently matches ask_pipeworx exactly', and ask_pipeworx_grounded), plus overlapping research tools like deep_research and validate_claim — an agent can easily misroute. The Watchmode cluster also blurs title_search vs list_titles and list_titles vs releases. The very detailed descriptions save it from a 1, but the ask_pipeworx_beta duplicate is a genuine selection hazard.

Naming Consistency4/5

Everything is snake_case and the clusters follow good prefixes — title_detail/title_search/title_seasons/title_sources, polymarket_edges/polymarket_arbitrage/polymarket_fill_risk, ask_pipeworx/ask_pipeworx_beta/ask_pipeworx_grounded. Minor inconsistency: scan_competitor_ai_presence and ai_visibility_check are sibling tools but don't share a naming pattern, and the pipeworx_*/ask_pipeworx*/plain-noun (genres, sources, regions) mix is slightly uneven. Still readable and mostly predictable.

Tool Count2/5

41 tools is heavy, but the real problem is scope: only ~10 of them are Watchmode streaming tools, while the rest are a Pipeworx data-router suite, a Polymarket/Kalshi prediction-market suite, memory, subscriptions, npm scanning, and llms.txt generation. This isn't a focused Watchmode server — it's three or four unrelated product surfaces bolted together under one name. Any single coherent feature area would justify closer to 10-15 tools.

Completeness3/5

The Watchmode core is actually well covered for a read-only catalog: search, detail, seasons/episodes, source availability, releases, and directory tools (genres/regions/networks/sources) make a complete browse-to-detail flow. But the overall surface is unfocused — AI visibility, npm deps, and llms.txt have nothing to do with the apparent purpose — and several tools are gated (deep_research needs an account, ask_pipeworx_grounded costs extra, ai_visibility_check needs a BYO key), leaving dead ends for anonymous agents.

Resources