propose_allocation
Propose strategic target allocation for your risk posture (conservative, moderate, or aggressive) and validate it against a canonical benchmark to check soundness. Read-only, no trades or recommendations.
Instructions
Propose a strategic target allocation for a risk posture (conservative / moderate / aggressive) over the user's book + the curated universe, and validate it against a canonical reference (60-40 / all-weather / permanent) with a held-out recent-window drawdown verdict. Use to answer 'what should a moderate portfolio look like for me, and is it sound'. Propose-only: never trades, never a recommendation or return forecast — every weight comes from the deterministic core. The weights are always returned; the verdict needs the reference tickers cached, else it's null with a warm note. Pass benchmark='none' to skip validation.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "propose_allocation"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| preset | No | moderate | |
| benchmark | No | 60-40 |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| asof | Yes | ||
| note | No | ||
| preset | Yes | conservative | moderate | aggressive | |
| verdict | No | held-out recent-window drawdown comparison; null when the reference history isn't cached (see validation_note) or validation was skipped | |
| weights | Yes | ||
| benchmark | No | reference requested for validation, or null when skipped | |
| validation_note | Yes | ||
| unpriced_holdings | No | held tickers with no cached price — the target was built over the priced subset, so a role's fund may differ from your actual dominant holding; warm the cache for the full picture |