Skip to main content
Glama

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. 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), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, premapped_pairing_unverified (always set in topic mode when 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[]. 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. 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

A4.6/5.0
Behavior5/5

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

The description goes well beyond the annotations (readOnly, openWorld, idempotent) by detailing the safety fields (compatibility_warning, compatibility_codes), explaining the meaning of each code, clarifying that unclassified legs are never paired, and describing how skipped comparisons are reported. It also reveals that returned pairs can still carry warnings and that pre-mapped pairs rely on keyword matching. This is rich, honest behavioral disclosure that the annotations alone do not supply.

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 every sentence carries significant information. It is front-loaded with the core purpose, then systematically covers modes, response structure, safety fields, and caveats. The use of labeled sections (TWO MODES, RESPONSE, SAFETY FIELDS) improves scannability. It could be trimmed slightly, but the complexity of the tool justifies the length; a 4 is appropriate.

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—two modes, multiple compatibility codes, alignment logic, and skipped-leg accounting—the description is remarkably complete. It explains the response structure, the significance of top_spreads_pp, the meaning of temporal_alignment, and how to interpret low_confidence_pairs and skipped fields. Since there is no output schema, the description carries the full burden and does so thoroughly. Nothing essential for correct invocation appears missing.

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 description coverage is 100%, so parameters are already documented. The description adds value by explicitly enumerating all ten topic shortcut values, providing example formats for the ticker and slug, and clarifying that explicit parameters override the topic-mapped side. This goes beyond the schema's basic descriptions, justifying a 4 rather than a baseline 3.

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 a clear, specific purpose: computing the cross-venue spread between Kalshi and Polymarket for the same resolving question. It names the two venues, the concept of a spread, and the condition of equivalence. It distinguishes itself from sibling tools like polymarket_arbitrage by focusing on across-venue matching rather than within-venue opportunities. The opening sentence is actionable and unambiguous.

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 explains when to use the tool: when comparing the same outcome across two prediction markets, and explicitly warns that most pre-mapped topics are not tradeable and will return compatibility_warning. It describes two usage modes (topic shortcuts vs explicit ticker/slug) and gives a clear caveat about real spreads being rarer than the shortcut list implies. It does not explicitly name alternative sibling tools, but the context signals provide enough direction. Thus a 4 is warranted.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation3/5

Many tools serve similar querying purposes (e.g., ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research) which could confuse an agent. However, detailed descriptions clarify differences, and some tools are very distinct (e.g., CIDR parsing, entity profile). Overlap is moderate but not severe.

Naming Consistency5/5

Tool names follow a consistent verb_noun pattern (e.g., resolve_entity, validate_claim, list_subscriptions) with underscores separating words. No mixing of styles like camelCase or abbreviations. Naming is clear and predictable.

Tool Count2/5

33 tools is excessive for a single server, covering areas as diverse as IP parsing, AI visibility, Polymarket betting, and SEC filings. This broad scope suggests the server tries to do too much, leading to a heavy and potentially unwieldy tool set.

Completeness3/5

The tool surface covers many domains (financials, prediction markets, IP tools, memory, subscriptions) but has notable gaps: no update for stored memories, limited subscription management (no modification), and some tools are marked as beta or deprecated. The set feels broad but not deep.