aipricepatterns

get_trading_decision

Return a compact trader decision card for a symbol/interval: TRADEABLE, WATCH, or SKIP with direction, confidence, evidence, risk, reasons, and caveats.

Input Schema

TableJSON Schema

Name	Required	Description
`f`	No	Forecast horizon in bars
`q`	No	Query length in bars
`sort`	No	Sort mode for results
`limit`	No	Maximum number of matches to return
`feePct`	No	Per-side fee percentage for the proof backtest
`symbol`	No	Ticker symbol (e.g., BTCUSDT)
`compact`	No	Default true: strips per-match value arrays and full forecast paths, returning match metadata, horizon-end price targets, and the calibrated outcome distribution (~4x fewer tokens). Set false for full arrays.
`minProb`	No	Minimum directional probability required to trade in the proof backtest
`anchorTs`	No	Target timestamp to search around
`interval`	No	Timeframe (e.g., 1h, 15m)
`token_id`	No	Optional Manus access token. Paid tools use tokenized service access, not a monthly subscription: when token_id is omitted the server returns payment_required with a Solana Pay invoice, and after payment you retry with the same token while the server uses Manus token/resolve to recover pending access.
`minAvgSim`	No	Minimum average similarity required to trade in the proof backtest
`slippagePct`	No	Per-side slippage percentage for the proof backtest
`backtestStep`	No	Backtest step in bars
`backtestEndTs`	No	Optional backtest end timestamp in Unix ms
`embeddingMode`	No	Pattern embedding mode: priceShape uses normalized closes, featureV1 uses OHLCV/context, neuralV1 uses the experimental ONNX encoder
`backtestMaxBars`	No	Maximum recent bars to load for the backtest
`backtestStartTs`	No	Optional backtest start timestamp in Unix ms
`includeBacktest`	No	When true, include a walk-forward backtest proof block. This is slower than the default decision-only response.
`backtestTimeoutMs`	No	Optional timeout budget for the backtest request

TDQS

B3.2/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden. It only describes the output card contents, but does not disclose that the tool may require a paid token, may return a payment_required response, or that it can optionally run a backtest (as implied by includeBacktest). It also doesn't mention performance characteristics or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the key action ('Return a compact trader decision card') and then lists the output components concisely. Every word adds value; there is no filler or redundancy.

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

Completeness2/5

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

For a tool with 20 parameters, no annotations, and no output schema, the description is incomplete. It explains the decision card output but omits the backtest proof block, the token payment mechanism, and the distinction between compact and full output modes. It does not provide enough context for an agent to know about important behaviors like includeBacktest or the need for token_id.

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 description coverage is 100%, so the baseline is 3. The description does not add parameter-level meaning beyond mentioning 'symbol/interval', which is already in the schema. It does not explain differences between parameters like f, q, embeddingMode, or backtest options.

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 clearly states the tool returns a 'compact trader decision card' with specific possible outcomes (TRADEABLE, WATCH, SKIP) and listed content fields (direction, confidence, evidence, risk, reasons, caveats). This is a specific verb+resource construction that distinguishes it from siblings like backtest_strategy or detect_market_regime.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. With a sibling tool like get_live_polymarket_trade_decision, the description does not clarify the difference or mention use cases. There is no context for when to prefer this over backtest_strategy or find_market_analogs.

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

All aipricepatterns tools Inspect

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

B3.2/5.0

Disambiguation2/5

Several tools inhabit overlapping territory: find_market_analogs, pattern_search, search_by_sketch, and get_candle_market_snapshot all relate to historical pattern matching, while get_trading_decision, get_trader_decision_v2, and get_live_polymarket_trade_decision all produce trade-oriented decisions. The descriptions add context, but an agent could still easily pick the wrong tool for a given request.

Naming Consistency3/5

The tools are consistently snake_case and mostly readable, but the naming conventions are mixed: many tools use get_<noun>, while others start with verbs like backtest, detect, find, forecast. Minor irregularities such as pattern_search and the v2 suffix in get_trader_decision_v2 also reduce predictability.

Tool Count4/5

Fifteen tools is within a reasonable size, and the server covers a broad domain: pattern search, regime detection, backtesting, track records, private datasets, live Polymarket decisions, and documentation. The count is not excessive, but some tools are functionally redundant enough that the set could be tightened.

Completeness4/5

The tool surface covers the main evidence workflow well: discovering patterns, analyzing analogs, backtesting strategies, checking track records, and producing trading decisions. Minor gaps remain around private dataset management and there is no separate low-level raw candle query tool, but most core user journeys are supported.

Resources

Need Help?