Skip to main content
Glama

Fcc

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. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, and the description adds substantial behavioral disclosure beyond those: it explains that both modes run the same token-overlap matcher, that compatibility codes can be non-empty even when pairs exist, that temporal_alignment null means 'could not be computed' rather than 'aligned', that spreads are gross and do not model Kalshi's fee schedule, and that unknown legs are never paired. This is precisely the kind of behavioral context an agent needs and the annotations do not provide.

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 and dense, but nearly every sentence carries a distinct operational fact: mode semantics, safety fields, code meanings, null semantics, fee caveats, and skipped-category counters. It is front-loaded with the core purpose and modes. The density is justified by the absence of an output schema, though the sheer length and all-caps section labels make it slightly harder to scan than an ideal tool description.

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 there is no output schema, the description takes on the full burden of explaining the return contract, and it does so thoroughly: leg-by-leg prices, top_spreads_pp with per-entry flags, compatibility_warning and compatibility_codes, temporal_alignment semantics, fees_note, skipped counters, and unclassified leg handling. An agent has enough context to invoke the tool, interpret its response, and avoid misreading warning fields as success indicators.

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%, and the schema already documents the topic list, kalshi_event_ticker, and polymarket_event_slug with examples. The description adds semantic value on top: the two-mode relationship between the parameters, that explicit parameters override the topic-mapped side, that both modes run the identical matcher, and that the same safety disclosures apply to both. This goes beyond the baseline 3 without duplicating schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific, concrete statement: a cross-venue spread between Kalshi and Polymarket for the same resolving question. It names the two venues, the quantity being computed (probability spread), and the two invocation modes (topic shortcuts vs explicit ticker/slug). It does not explicitly name a sibling tool as an alternative, but the purpose is far beyond a tautology and an agent can tell what the tool does.

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?

The description gives clear context for when to use each mode: topic shortcuts for pre-mapped macro events and explicit ticker/slug for custom pairings. It also warns that pre-mapped topics often return compatibility warnings and that pre-mapped does not mean tradeable. It does not name alternatives among siblings such as polymarket_arbitrage, so it stops short of explicit when-not-to-use guidance, but the mode-selection guidance is strong and concrete.

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

All Fcc 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
Disambiguation3/5

Several tools cluster around the same core purpose: the three ask_pipeworx variants, the three census reverse-geocoders, and the six Polymarket analysis tools. Descriptions are detailed enough to disambiguate most choices, but ask_pipeworx_beta is currently identical to ask_pipeworx, creating genuine ambiguity. An agent could easily select the wrong tool in these overlapping families.

Naming Consistency3/5

Names mix verb-initial actions (ask_pipeworx, compare_entities, resolve_entity) with noun-initial compound names (census_block, entity_profile, polymarket_edges). The polymarket_* family is internally consistent, but the set as a whole lacks a uniform verb_noun convention. Single-word verbs like remember, recall, and forget further break the pattern.

Tool Count2/5

At 34 tools, this exceeds the 'too many' threshold of 25 and includes clear redundancy: ask_pipeworx_beta duplicates ask_pipeworx, county_for_point is a thin wrapper over the same service as census_area/census_block, and scan_competitor_ai_presence just loops ai_visibility_check. The broad scope does not justify this many tools, and the set would be better split into focused servers.

Completeness4/5

Each sub-domain has solid lifecycle coverage: memory has remember/recall/forget, subscriptions have subscribe/list/unsubscribe/recent_alerts, and company research has resolve_entity/entity_profile/compare_entities/recent_changes. Minor gaps exist (e.g., no direct pipeworx:// citation-fetching tool), but no critical dead ends that would cause agent failures.

Resources