Back to MCP catalog
get_walk_forward

Get the status and results of a walk-forward analysis run.

Area

Backtesting & Validation

Group

Robustness

Access

Read

Risk

Read-only

Details

Full description

Get the status and results of a walk-forward analysis run. Poll after walk_forward() returns until status="completed" or "failed".

Argswalk_forward_id from walk_forward().

Level 1 (no sweep) returns:

  • oos_sharpe_mean / oos_sharpe_std — mean and std of out-of-sample Sharpe across windows
  • pct_profitable_windows — fraction of OOS windows with positive return
  • per_window — per-window range, sharpe, total_return, trades

Level 2 (with sweep) additionally returns:

  • wfe_mean — mean Walk-Forward Efficiency (OOS Sharpe / IS Sharpe); closer to 1.0 means OOS tracked in-sample
  • parameter_stability — selected parameter values per param key, one per valid in-sample window
  • per_window — is_range, oos_range, is_sharpe, oos_sharpe, wfe, selected_params

Capabilities

Bounded options and operating modes surfaced above the full JSON schema.

No bounded capability options are declared for this tool.

Required Inputs

walk_forward_idstringWalk-forward run identifier

Optional Inputs

per_window_limitintegerMax per_window entries to return (default 50, max 200).
per_window_offsetintegerNumber of leading per_window entries to skip for paging.
Quawd

A subscription SaaS platform for designing, backtesting, and paper-trading algorithmic trading strategies on equities and crypto — described in plain English to an AI agent, no code required.

© 2026 Quawd. All rights reserved.

Quawd is a software tool, not a broker-dealer or investment adviser, and does not provide investment advice. Trading involves substantial risk of loss. Backtested and hypothetical results have inherent limitations and are not indicative of future performance.