Skip to main content
Glama

Goproxy

by io.github.pipeworx-io

Bet Research

bet_research
Read-onlyIdempotent

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
depthNoquick = 2-3 evidence sources, thorough = full fan-out. Default thorough.
marketYesPolymarket slug ("will-bitcoin-hit-150k-by-june-30-2026"), full URL ("https://polymarket.com/event/..."), or question text ("Will Bitcoin hit $150k by June 30?")
include_rawNoDefault false. When false (recommended), FRED/FDA/GDELT/Federal-Register evidence is summarized to the few fields agents actually use — keeps responses under ~20KB. Pass true to get full upstream payloads (50KB-500KB) when you need to recompute deltas, cite specific observations, or post-process.

Schema Changelog

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

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "market_input": "will fed cut rates in june 2026"
-  },
-  {
-    "market_input": "https://polymarket.com/event/will-bitcoin-hit-150k-by-june-30-2026"
-  }
-]New value: +[
+  {
+    "market": "will-bitcoin-reach-100k-in-july-2026"
+  },
+  {
+    "market": "https://polymarket.com/event/will-bitcoin-hit-150k-by-june-30-2026"
+  }
+]
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "market_input": "will fed cut rates in june 2026"
+  },
+  {
+    "market_input": "https://polymarket.com/event/will-bitcoin-hit-150k-by-june-30-2026"
+  }
+]
  3. Changed1 schema field changed
    • addedInput schema / properties / include_raw
      Added value: +{
+  "description": "Default false. When false (recommended), FRED/FDA/GDELT/Federal-Register evidence is summarized to the few fields agents actually use — keeps responses under ~20KB. Pass true to get full upstream payloads (50KB-500KB) when you need to recompute deltas, cite specific observations, or post-process.",
+  "type": "boolean"
+}
  4. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint false), the description reveals behavioral traits: low-confidence matches short-circuit with status, closed markets skip fan-out, wide spreads flag illiquidity, and resolution-rule risk parsing. It details response shape and edge-case handling, adding substantial context annotations alone 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 but densely informative, with a logical structure: purpose, usage, classifiers, fan-out examples, response shapes, resolver contract, parent events, news fields, safety. Every sentence adds value, though it could be slightly more concise without losing essential details.

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 absence of an output schema, the description covers all bases: input specification, behavioral nuances (e.g., market match confidence, cancellation rules), error states (low_confidence_match, market_closed_or_inactive), and guidance for interpreting results. An AI agent has sufficient context to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds rich meaning: market accepts slug, URL, or question text; depth enum explained as 'quick = 2-3 evidence sources, thorough = full fan-out'; include_raw default false with guidance on when to set true. Examples in input schema reinforce usage.

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 starts by stating the tool 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call,' clearly indicating the verb (research), resource (Polymarket bet), and scope (single call). It specifies input types (slug, URL, question text) and distinguishes itself from sibling tools focused on general queries (ask_pipeworx) or claim validation (validate_claim).

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 explicitly says 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z"' and provides examples of classification and fan-out. It advises inspecting resolver contract fields and warns about low-confidence matches, but does not explicitly state when to avoid this tool or compare to alternatives.

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

All Goproxy 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

B3.1/5.0
Disambiguation2/5

Several tool families overlap heavily: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical entry points, while discover_tools/suggest_questions and entity_profile/compare_entities/recent_changes serve similar discovery/comparison roles. The polymarket_* cluster also has tightly related boundaries that require reading long descriptions to disambiguate, and version-related helper tools (go_mod, module, versions, version_info) add further confusion.

Naming Consistency3/5

Most tools follow a lowercase snake_case verb_noun pattern (list_subscriptions, resolve_entity, validate_claim), but there are notable deviations: bare verbs like remember/recall/forget, noun-only names like go_mod, module, versions, and version_info, and brand-prefixed names like ask_pipeworx and pipeworx_feedback. The naming is readable and generally predictable, yet the mix of conventions keeps it from being highly consistent.

Tool Count2/5

With 35 tools, the surface is heavy for what is ultimately a data-access and research server. Many tools are conveniences or meta-wrappers that could be consolidated (e.g., three ask_pipeworx variants, multiple polymarket scanners, several onboarding/discovery tools). While the breadth is intentional, 35 feels bloated rather than well-scoped.

Completeness4/5

The toolset covers a remarkably broad domain: universal data lookup, grounded fact-checking, entity resolution, company profiles, comparisons, prediction-market analysis, memory, subscriptions, and feedback. Minor gaps exist—subscriptions can be created/cancelled but not updated/paused, and there is no direct resolver for pipeworx:// citation URIs—but these are workable and core workflows have no dead ends.

Resources