Skip to main content
Glama

Tarot Draw

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.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "topic": "fed"
+  },
+  {
+    "topic": "btc"
+  }
+]
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnly/openWorld/idempotent/non-destructive. The description adds substantial behavioral context: compatibility_warning can be non-empty even when matched_pairs>0, null temporal_alignment means 'could not compute', Kalshi fees are not modeled so spreads are gross not net, and unclassified legs are never paired. It also enumerates machine-readable codes and per-entry flags. 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but almost every sentence carries unique caveats or disclosures (fees note, skipped counters, 'pre-mapped ≠ tradeable'), and the first sentence nails the core purpose. It loses a point because it's an unstructured wall of text—section headers or bullet lists would make the safety-field semantics easier 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 remarkably complete: it covers response structure (leg-by-leg prices, top_spreads_pp, skipped counts), every safety field and code, temporal alignment semantics, and the fee caveat. An agent can determine call semantics, interpretation, and failure modes from the description alone.

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%—each parameter has a description and lists the topic options. The tool description goes beyond by explaining that both modes run the identical token-overlap matcher, that explicit tickers override the topic-mapped side, and that custom pairings are for cases where no pre-map exists. This adds interaction-level meaning not present in 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?

Opens with a specific declarative: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question.' It identifies the resource (the two venues, same question), the metric (spread in pp), and even explains why the spread can be a real signal, separating it from sibling tools like polymarket_arbitrage or polymarket_edges.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clearly distinguishes TWO MODES—pre-mapped topic shortcuts versus explicit kalshi_event_ticker+polymarket_event_slug pairings—and explains when each is appropriate. It also warns that pre-mapped does not equal tradeable, but it does not name sibling tools or explicitly state when to prefer them over this tool.

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

All Tarot Draw 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

A3.7/5.0
Disambiguation2/5

Multiple tool families have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, suggest_questions and discover_tools are near-duplicates, and ai_visibility_check is a subset of scan_competitor_ai_presence. The five polymarket_* tools are heavily overlapping in purpose and rely on long descriptions to distinguish them, which an agent must read carefully to avoid misselection.

Naming Consistency3/5

All names are lowercase snake_case and there are helpful prefixes (polymarket_*, ask_pipeworx_*, pipeworx_*), but the verb/noun ordering is inconsistent: verb-first names (generate_llms_txt, resolve_entity, scan_dependency) sit alongside noun-first names (bet_research, entity_profile, recent_changes) and bare verbs (forget, recall, remember). Sub-families are internally consistent, but the set as a whole follows no single convention.

Tool Count2/5

32 tools is over the 'too many' threshold, and the scope is a grab-bag rather than a focused server: data research, prediction-market analysis, npm dependency checks, llms.txt generation, memory utilities, subscriptions, and exactly one tarot tool. The server is named 'Tarot Draw' yet 31 of 32 tools serve a completely different purpose, making the count wildly mismatched to the apparent identity.

Completeness2/5

For the inferred Pipeworx data/prediction-market domain the coverage is genuinely deep — ask/grounded/deep research, entity resolution, profiles, comparisons, validation, subscriptions, alerts, edge tracking, and arbitrage all exist. But for the stated purpose ('Tarot Draw'), the surface is one draw tool with no deck details, spreads, reading history, or reversal support, and the data tools' domain is so diffuse that an agent cannot rely on the set forming a coherent workflow.

Resources