Skip to main content
Glama

Ebi Ols

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.

TDQS

A4.4/5.0
Behavior5/5

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

The annotations already declare readOnly/idempotent/non-destructive, but the description goes far beyond that. It exposes resolver confidence levels and alternatives, parent_event extraction, news fallback fields, safety short-circuits (low_confidence_match, market_closed_or_inactive, illiquid_wide_spread), and cancellation-rule parsing. These details are critical for interpreting results correctly and safely, especially for an agent that might otherwise size bets based on unreliable matches.

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 it is efficiently structured into labeled sections (CLASSIFIERS, FAN-OUT, RESPONSE SHAPES, RESOLVER CONTRACT, SAFETY, etc.) and front-loaded with the primary purpose. Every section provides actionable information for correct tool usage, though some redundancy exists (e.g., re-explaining the closed-market path). It is not concise in word count but is internally organized and information-dense.

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?

With no output schema present, the description carries the full burden of explaining return values, and it does so thoroughly: response shapes for market/analysis/evidence, resolver contract with confidence/alternatives/suggestions, parent_event structure, news fallback fields, and blocking statuses. It also warns about cancellation-rule risk, which is essential for bet sizing. The description gives agents everything needed to use the tool correctly and handle edge cases.

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

Parameters3/5

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

The schema covers all 3 parameters with detailed descriptions (100% coverage), including the market input variants, the depth enum, and the include_raw payload size trade-off. The description adds contextual fan-out examples and classifier lists, but these do not materially change the meaning of the parameters themselves. Baseline 3 is appropriate since schema does the heavy lifting.

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 with a specific verb and resource: “Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.” It states the input types (slug/URL/question text), the action (resolve, classify, fan-out, compare), and the output (evidence packet + market-vs-model comparison). Explicit use cases “should I bet on X” and “is there edge in Z” further distinguish it from generic ask/search tools.

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 clearly states when to use the tool: “Use for 'should I bet on X', 'what does the data say about Y', or 'is there edge in Z'.” It also provides warnings about blocking statuses and cancellation-rule checks before sizing bets. However, it does not explicitly name alternatives or give when-not-to-use guidance, so it falls short of the top bar.

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

All Ebi Ols 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

B3.3/5.0
Disambiguation2/5

Many tools have overlapping purposes, especially among Pipeworx query tools (ask_pipeworx, ask_pipeworx_grounded), betting research tools (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_kalshi_spread), and memory tools (remember, recall, forget). An agent could easily select the wrong tool. Additionally, tools like 'discover_tools', 'search', and 'search_within' have unclear boundaries.

Naming Consistency3/5

Most tool names use snake_case (e.g., 'entity_profile', 'validate_claim'), but there are inconsistencies with single-word verbs like 'forget', 'recall', 'remember', 'subscribe', 'unsubscribe', and the mixed pattern of 'ask_pipeworx' vs 'pipeworx_feedback'. Overall, the naming is somewhat consistent but not fully predictable.

Tool Count3/5

With 32 tools, the server has a high but not extreme count. However, the tools span multiple unrelated domains (ontologies, financial data, betting, memory, subscriptions, AI visibility), making the server feel like a collection of disparate features rather than a focused toolset. This reduces the appropriateness of the count for a single server.

Completeness2/5

The tool surface has significant gaps. For example, ontology tools lack create/update/delete operations; betting tools only provide research and analysis but no placement; memory tools allow save/recall/delete but not update; and there is no tool for user authentication or account management despite subscription features. The server covers many areas but none completely.

Resources