Skip to main content
Glama

Facebook_ads

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?

The description goes far beyond the readOnly/idempotent annotations: it discloses that matching is keyword/overlap based, that Kalshi fees are not modeled, that spreads are gross, that unclassified legs are never paired, and that null temporal_alignment does not mean aligned. This is exemplary behavioral disclosure.

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 well-structured with labeled sections (TWO MODES, RESPONSE, SAFETY FIELDS) and front-loaded key information. It is quite long, but nearly every sentence carries safety or matching context; a lighter edit could preserve the value while reducing length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with no output schema, the description covers response fields, compatibility codes, skipped-leg counters, fee caveats, and matching limitations thoroughly. The only notable omission is behavior when called with no parameters at all, especially since all parameters are optional.

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?

The schema already covers all three parameters at 100% coverage, and the description adds meaningful mode semantics: topic pre-maps events while the explicit parameters override the mapped side, and both modes run the same matcher. It does not add much beyond that, but the mode relationship is genuinely useful.

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 by naming the exact deliverable — a cross-venue spread between Kalshi and Polymarket for the same resolving question — which immediately separates it from Polymarket-only siblings. The two-mode breakdown and response summary make the tool's function concrete 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?

It clearly explains when to use the topic shortcuts versus explicit ticker/slug pairings, and warns that pre-mapped topics often return compatibility warnings. It does not explicitly route the agent away from sibling tools like polymarket_edges or polymarket_arbitrage, so it stops just short of a 5.

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

All Facebook_ads 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

A3.6/5.0
Disambiguation4/5

The 11 fb_* Facebook tools are clearly separated by resource (account vs campaign vs adset) and action (list vs get vs create), and the Pipeworx research tools each have distinct roles (router, grounded, profile, compare, research). However, ask_pipeworx, ask_pipeworx_beta, and deep_research overlap in routing/fan-out behavior, and ai_visibility_check vs scan_competitor_ai_presence are near-identical in purpose, creating some ambiguity.

Naming Consistency3/5

The 11 fb_* tools follow a consistent fb_verb_noun pattern (except fb_get_campaign vs fb_list_*), but the remaining 25+ tools mix verb-first (ask_pipeworx, compare_entities, resolve_entity), noun-first (entity_profile, recent_changes, polymarket_edges), and generic names (forget, recall, remember). Pipeworx tools use verb_noun mostly consistently (ask_pipeworx, discover_tools, resolve_entity) but the overall set blends two naming cultures without a unifying prefix or pattern.

Tool Count3/5

36 tools is on the heavy side for one server. The Facebook ads domain only needs ~11 tools, while the rest are a sprawling Pipeworx research/meta platform (memory, subscription, prediction-market, web-tooling, AI-visibility) that feels like several servers merged into one. Each area is internally coherent, but as a single MCP server the count is bloated.

Completeness4/5

The Facebook ads surface covers list accounts/campaigns/adsets and read campaigns/insights, but notably lacks create/update/delete operations for campaigns and adsets, so the ad-management workflow has dead ends. The Pipeworx research side is extremely complete for data lookup (router, grounded, deep research, entity profiles, comparisons, verification), though the memory/subscription tools introduce a separate domain that is only thinly supported.

Resources