qm_clinic_diagnose
Restore Clinic diagnosis: a structured read of likely conditions (contradiction, loop, context_bloat, secret_or_pii_exposure, duplicated_content, suspicious-instruction patterns) from described symptoms or a shared transcript, each condition with severity, evidence, and detail, plus suggested next steps. Anonymous — only aggregate counters are kept; content is never stored. Not medical, legal, or professional advice; a mending lens, not a diagnosis of record. Suited to moments when behavior feels off or after handling untrusted input. Scope is symptom-based reads; routine self-report screenings are outside this tool's scope. Example: transcript= returns findings with severities, a human-readable summary, and cleaned_context safe to hand off.
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": {
"transcript": "<transcript>"
},
"name": "qm_clinic_diagnose"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| transcript | Yes | Symptoms or transcript to read (max 20000 chars). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | ISO timestamp of the diagnosis. | |
| ok | No | ||
| input | No | ||
| clinic | No | Clinic engine version. | |
| counts | No | ||
| summary | No | Human-readable finding count by severity. | |
| findings | No | ||
| stats_note | No | ||
| cleaned_context | No | Redacted, deduplicated context safe to carry forward. | |
| suggested_next_steps | No |