Skip to main content
Glama

Apology

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

A4.5/5.0
Behavior5/5

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

Even though readOnlyHint/openWorldHint/idempotentHint already cover safety, the description adds substantial non-obvious behavior: compatibility_codes semantics, unclassified legs never being paired, temporal_alignment null meaning, gross-vs-net fee disclosure, and skipped comparison counters. It also explains that pairing is keyword-based and not verified by a shared resolution source. This gives the agent critical interpretive context for the response.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The description is dense, organized into mode/response/safety sections, and front-loads the core purpose before caveats. However, it is quite long and packs many nested caveats and code enumerations into continuous prose, so it places a heavy reading burden on the agent; it could be trimmed without losing value.

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?

For a tool with no output schema, the description fully covers return fields, flags, codes, edge cases, and fee implications. It even clarifies the null semantics of temporal_alignment and explains skipped_cross_type/subtype counters. An agent has enough information to call the tool in either mode and interpret the result 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 coverage is 100%, so the schema already documents all three parameters. The description adds meaning by explaining that topic auto-fetches a pre-mapped event on both venues, that the two explicit parameters override the mapped sides, and that both modes run the same token-overlap matcher. This is helpful but rests on a solid schema baseline.

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 states precisely that the tool computes the cross-venue spread between Kalshi and Polymarket for the same resolving question, and it goes on to specify two modes and the response contents. It distinguishes itself from single-venue or generic research siblings by emphasizing cross-venue pairing and the same-question requirement. This is far beyond a tautology and gives an agent a concrete model of what the tool returns.

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?

It gives clear usage context: topic mode for pre-mapped shortcuts and explicit mode for custom kalshi_event_ticker/polymarket_event_slug pairings, and it warns that most pre-mapped topics return compatibility warnings and are not necessarily tradeable. It does not name sibling tools like polymarket_arbitrage or say when to prefer them, so it stops short of full alternative routing.

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

All Apology 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

ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-duplicates with beta explicitly identical to the stable version, causing potential misselection. ai_visibility_check and scan_competitor_ai_presence overlap heavily, and resolve_entity/discover_tools/ask_pipeworx all serve lookup purposes. Many tools are distinct, but the boundaries around the core query tools are blurry.

Naming Consistency2/5

Naming is inconsistent: mostly snake_case but mixed verb styles (ask_pipeworx vs pipeworx_feedback vs resolve_entity), brand prefixes applied irregularly, and no uniform convention (e.g., subscribe/unsubscribe/list_subscriptions vs forget/remember/recall vs polymarket_arbitrage/edges/edge_tracker). Some names are descriptive, but the set lacks a predictable pattern.

Tool Count2/5

32 tools is above the 25 threshold for a heavy surface, and the server mixes unrelated domains (data lookup, prediction markets, memory, subscriptions, AI visibility, apology generation). While a large data platform could justify many tools, the random inclusions (apology_generate, generate_llms_txt, scan_dependency) suggest a lack of scoping. Several tools could be consolidated without loss.

Completeness4/5

For the dominant data-research/prediction-market domain, coverage is strong: lookup, grounded verification, research, entity resolution, comparison, arbitrage scanning, fill risk, subscriptions, memory, and discovery are all present. Minor gaps exist (no direct account management beyond subscriptions, no tool to modify stored memories), but agents can mostly achieve their goals. The stray non-domain tools do not hurt completeness of the core platform.

Resources