Skip to main content
Glama

Bundlephobia

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

A4.9/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint false), the description discloses important behavioral nuances: the semantic anchor threshold (Jaccard ≥0.30), partition filter placeholder logic, and the fill check condition 'realizable_edge_pp ≤ 0 means... do not trade it'. It also explains the response structure and edge cases, adding substantial context beyond the structured fields.

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 quite long but extremely well-structured with labeled sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK) and bolded mode emphasis. Every sentence adds unique, non-redundant context. It is not concise, but the complexity of the tool justifies the length; the structure makes it easily scannable.

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?

There is no output schema, so the description carries the full burden of explaining return values, which it does thoroughly: 'Response: opportunities[] (gap_pp, suggested_trade, reasoning...) and in event mode partition_check{...}'. It also covers edge cases, thresholds, and what to do when the signal is not tradeable. For a tool with complex behavior and no output schema, this is complete.

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 goes far beyond the schema. It explains what event slugs look like with examples, what topic seed questions work, and what each mode does internally (e.g., 'walks child markets, checks date-axis / threshold-axis ordering'). It adds meaning that the input schema does not provide, such as accepting full URLs and describing cross-event behavior.

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 action: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It clearly distinguishes three modes (trending_scan, event, topic) and differentiates from siblings by explaining the exact methodology. This is a textbook example of purpose clarity with specific verb+resource+scope.

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 explicitly tells when to use each mode: 'Call with NO args for a trending_scan' and 'event (recommended for a specific market)' vs 'topic (for cross-event scanning)'. It even names an alternative tool: 'For custom sizing use polymarket_fill_risk.' This exceeds the bar for usage guidance.

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

All Bundlephobia 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

A3.9/5.0
Disambiguation2/5

There is substantial overlap among tools in the Pipeworx group: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all route natural-language queries to the same 5,578 tools and sources, with only subtle differences in mode (beta vs stable, grounded vs standard, single vs multi-part). Similarly, polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, and polymarket_fill_risk are heavily intertwined, making differentiation difficult. Tools like similar, size, history, and scan_dependency from the bundlephobia side are distinct, but the Pipeworx family muddies the set.

Naming Consistency3/5

The bundlephobia tools follow a consistent noun pattern (size, similar, history), and the Pipeworx meta-tools use snake_case verbs (ask_pipeworx, resolve_entity, compare_entities, validate_claim). However, the naming is inconsistent across the two families—bundlephobia's simple nouns (size, similar, history) clash with the verbose descriptive verbs—and naming like ai_visibility_check, scan_competitor_ai_presence, and generate_llms_txt break from the Pipeworx pattern. The set mixes short names, camelCase-ish compounds, and snake_case, so no single consistent convention holds.

Tool Count2/5

35 tools is too many for a server that ostensibly serves two domains (bundle-size analysis and Pipeworx data research). The bundle-size analysis needs only a handful (size, history, similar, recent_searches, scan_dependency), yet there are over 30 tools dominated by a sprawling meta-research layer including multiple ask_pipeworx variants, several polymarket tools, plus meta-cognitive tools (remember, recall, forget, discover_tools) that are not core to either domain. This bloats the surface and makes call routing difficult.

Completeness4/5

Each functional domain is fairly complete: bundlephobia covers size measurement, history, alternatives, search, and dependency vetting; the Pipeworx side covers lookup, research, entity resolution, comparison, verification, subscriptions, and feedback. However, there are gaps—e.g., no tool for directly reading an npm package's README or license beyond scan_dependency's summary, and no explicit tools for some administrative actions like account management or subscription editing beyond create/cancel/list. The completeness is strong for what's advertised but not exhaustive.

Resources