find_sweep_runs
Runs from one sweep, or from every sweep this person has, filtered and sorted by the engine. LEAVE experiment_id OUT to search them all, which is how a person asking whether they have already found something like this gets an answer without spending a new search on a question that already has one. A SWEEP HAS NO WINNER: which run matters depends entirely on what was being asked, so you choose sort_by for the question in front of you -- return, risk-adjusted return, drawdown, trade count -- and say which one you sorted by whenever you report an order. Never call the top row 'the best strategy'; it is the top row by the measure you picked. Filter before you sort: a run with a handful of trades has metrics that mean nothing, so min_trades is usually the first thing to set. Every numeric filter has BOTH bounds, so a band is one question: a delta against the benchmark between 3 and 8 is min and max together, not a page fetched and thinned by hand. Readable while the sweep is still running. At most 50 runs per call (default 20); pass offset to read on.
[Access: pay 0.005 USDC via x402 (PAYMENT-SIGNATURE header) OR authenticate with an API key. An x402-capable client will auto-pay; API-key clients pay nothing per call.]
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"sort_by": "<sort_by>"
},
"name": "find_sweep_runs"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| asset | No | Asset symbol, e.g. BTC or ETH. | |
| limit | No | Maximum results. | |
| order | No | desc for best-first on that metric, asc for worst-first. | desc |
| trend | No | Only runs from windows of this trend character, e.g. clean or choppy; several comma-separated, any of them counts. | |
| offset | No | Pagination offset in the result units documented by the tool; zero starts the first page. | |
| max_irr | No | Only runs at or below this annualised IRR. | |
| min_irr | No | Only runs at or above this annualised IRR. | |
| sort_by | Yes | The metric to order by, e.g. sharpe_ratio, sortino_ratio, irr_annualized, total_return, max_drawdown, total_trades. Required, because the choice IS the question being asked. | |
| covering | No | Only runs over windows covering this single date, as YYYY-MM-DD. A different question from a span. | |
| run_index | No | Which run, as find_sweep_runs reported it. | |
| atr_period | No | Only runs that used this ATR period. Needs experiment_id. | |
| generation | No | Only runs from this engine generation, so runs made under different engine behaviour are not compared as though alike. | |
| max_return | No | Only runs at or below this total return. | |
| max_sharpe | No | Only runs at or below this Sharpe ratio. | |
| max_trades | No | Only runs at or below this trade count. Pairs with min_trades to ask for a band rather than a floor. | |
| min_return | No | Only runs at or above this total return. | |
| min_sharpe | No | Only runs at or above this Sharpe ratio. | |
| min_trades | No | Drop runs with fewer trades than this. Metrics from a handful of trades are noise. | |
| run_status | No | Only runs with this outcome, e.g. no_trades for the ones that never opened a position. | |
| volatility | No | Only runs from windows of this volatility band, e.g. low; several comma-separated, any of them counts. | |
| candle_size | No | Duration of one candle, e.g. 1h or 1d. | |
| covering_to | No | Only runs whose window overlaps up to this date. | |
| max_win_rate | No | Only runs at or below this win rate. | |
| min_win_rate | No | Only runs at or above this win rate. | |
| trigger_name | No | Only runs whose entry trigger is this signal. | |
| cooldown_bars | No | Only runs that used this cooldown. Needs experiment_id. | |
| covering_from | No | Only runs whose window OVERLAPS this date onwards. A run is relevant to 2024 if any of it happened in 2024. | |
| experiment_id | No | The sweep, as create_sweep returned it. | |
| reward_factor | No | Only runs that used this reward-to-risk setting. Execution filters need experiment_id; the cross-sweep surface does not serve them. | |
| beats_benchmarks | No | Only runs that beat all three benchmarks over the same | |
| market_direction | No | Only runs from windows of this market character, e.g. bear or mega_bull. Several are one comma-separated string, e.g. "bull,super_bull", and a run matching any of them counts. What a run did in one kind of market says little about another. | |
| regime_composite | No | Only runs from windows with this full regime label, e.g. mega_bull_high_clean, when the three parts together matter; several comma-separated, any of them counts. Across different regime filters every one must hold. | |
| regime_direction | No | The direction band from get_market_regime, e.g. bear. The signal searches filter by it and find_sweep_runs marks each row's regime_fit with it; save_strategy and update_strategy read the current band themselves, so their check runs without it. | |
| max_delta_vs_asset | No | Only runs beating their own asset by at most this much. | |
| max_risk_per_trade | No | Only runs that risked this fraction per trade. Needs experiment_id. | |
| min_delta_vs_asset | No | Only runs beating buy-and-hold on their own asset by at least this much. | |
| max_delta_vs_benchmark | No | Only runs beating their benchmark by at most this much, so "between 3 and 8" is one question rather than a page fetched and thrown away. | |
| min_delta_vs_benchmark | No | Only runs that beat their benchmark by at least this much. A return in a rising market is not skill. | |
| beats_crypto_benchmarks | No | Only runs that beat the crypto benchmarks rather than only their own asset. |