Skip to main content
Glama

Codewars

by io.github.pipeworx-io

Polymarket–Kalshi Spread

polymarket_kalshi_spread
Read-onlyIdempotent

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) topic — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit kalshi_event_ticker + polymarket_event_slug for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (they resolve in different months), temporal_alignment_unknown (the resolution month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event's close/strike date yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period, in EITHER mode; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. spread.fees_note is a standing disclosure: Kalshi charges per-contract trading fees, Polymarket does not, and this tool does not model Kalshi's fee schedule — every spread_pp is gross, not a net tradeable edge. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNoPre-mapped: fed | btc | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president
kalshi_event_tickerNoExplicit Kalshi event ticker, e.g. "KXFED-26OCT". Overrides the topic-mapped Kalshi side.
polymarket_event_slugNoExplicit Polymarket event slug, e.g. "fed-decision-in-june-825". Overrides the topic-mapped Polymarket side.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, but the description goes far beyond that. It discloses that spreads are gross and do not model Kalshi's fee schedule, explains each compatibility code and when it is set, details how temporal alignment is computed and that null does not mean aligned, and reveals that legs with 'unknown' metric_type are never paired. All of this adds significant behavioral context beyond the 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 exceptionally well-structured: it front-loads the purpose, then breaks into labeled sections (TWO MODES, RESPONSE, SAFETY FIELDS) with clear formatting. Each sentence carries distinct information – mode selection, output structure, safety codes, fee note, skipped categories – with no filler. The density is appropriate for a tool with this complexity, so it earns its length.

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 comprehensively covers the response structure: per-leg prices, matched spreads, compatibility_warning/codes, per-entry flags, temporal_alignment fields, fees_note, and skipped counters. It also explains edge cases (null alignment, unknown legs) and the meaning of each code. An agent has everything needed to invoke the tool correctly and interpret results.

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% – every parameter is documented in the schema. The description complements this by explaining that 'topic' provides pre-mapped shortcuts, that explicit ticker/slug override the topic-mapped sides, and that both modes use the same matcher. This adds contextual meaning beyond the schema's descriptions, though the schema already covers the basic syntax and examples.

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 'Cross-venue spread between Kalshi and Polymarket for the same resolving question,' precisely naming the verb (compare/spread), the resources (Kalshi and Polymarket), and the focus (same resolving question). It further explains that the tool surfaces price differences and flags when bet shapes are non-equivalent, clearly distinguishing it from single-venue tools. It also contrasts with sibling tools like polymarket_arbitrage by emphasizing the cross-venue spread rather than arbitrage execution.

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?

It explicitly describes two usage modes (topic shortcuts vs. explicit ticker/slug), when to use each, and that both run the identical matcher. It warns that pre-mapped topics frequently return compatibility_warning and that 'pre-mapped ≠ tradeable,' guiding the agent to interpret results cautiously. It also instructs to read safety fields even when matched_pairs>0, and explains skipped categories, giving clear do/don't guidance.

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

All Codewars 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

A3.5/5.0
Disambiguation2/5

The 4 Codewars tools (kata, user, user_authored, user_completed) are distinct, but the 31 Pipeworx tools create real overlap: ask_pipeworx, ask_pipeworx_beta (explicitly 'currently matches ask_pipeworx exactly'), and ask_pipeworx_grounded are near-twins of the same router, and the five polymarket_* tools (edges, arbitrage, edge_tracker, fill_risk, kalshi_spread) have heavily overlapping opportunity-discovery purposes. discover_tools and suggest_questions also both serve as 'what can I ask' entry points. Agents will misselect between the three ask_pipeworx variants and across the prediction-market suite.

Naming Consistency2/5

Naming conventions are mixed: bare nouns (kata, user), bare verbs (forget, remember, subscribe), adjective_noun (recent_alerts, recent_changes), verb_noun (validate_claim, bet_research), and noun_verb (user_authored, user_completed) all appear. Even within the small Codewars family the prefix style is inconsistent — kata and user are bare nouns while user_authored and user_completed expect a user_ prefix, and remember/recall/forget use a different verb style than the rest of the server.

Tool Count2/5

35 tools exceeds the 25+ 'too many' threshold for a coherent server. Worse, 31 of the 35 are Pipeworx meta-research tools unrelated to the server's namesake (Codewars), so the count is drastically inflated relative to its apparent purpose — the server presents a full finance/prediction-market/research gateway while contributing only 4 tools to its advertised domain.

Completeness2/5

The actual Codewars surface has significant gaps: kata, user, user_authored, and user_completed are purely read-only, with no solution submission, attempt/training history, leaderboard access, or kata search by difficulty/language. Meanwhile the Pipeworx side is over-complete for a server not named for it, leaving the server's stated identity under-covered with no way to perform any write operation on the Codewars platform.

Resources