evaluate
Run clinical risk-score calculations treating missing findings as unknown, not normal, to see if the decision is settled, all possible categories, score range, and unknowns worth asking about.
Instructions
Evaluate a calculator on what is actually known.
findings maps item ids to values: "present" / "absent" for boolean items, one of the
listed levels for ordinal items, a number for numeric items ("normal" for those with a
normal range, when the note gives no number; {"min": x, "max": y} when it gives only
bounds). Omit items that are not documented (or send "unknown"); they are treated as
unknown, never as normal.
Returns whether the decision category is settled, every category still possible, the worst case, the score range, and the decisive unknowns: the only items worth asking the clinician about, each with what the category would be for each possible answer.
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": {
"calculator_id": "<calculator_id>"
},
"name": "evaluate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| findings | No | ||
| calculator_id | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||