explain_silence
Read-onlyIdempotent
Explain why a watched trip has produced no updates.
Use this tool when the user asks why they have not heard anything about
a watched trip. Returns {recheck_count, last_checked} (proof the trip
was actively monitored),
{suppressed:[{what, domain, country, score, floor, reason}]} (what we saw
for your destinations and dropped below the disclosed relevance floor —
e.g. a deep quake at modelled felt-intensity 3.39 < floor 4.0),
{confidence_during_window} (same recency input as assess_trip), and
{blind_spots:[{domain, country, note}]} — domains/countries we do NOT
monitor live, so silence there is NOT a guarantee (e.g. aviation-IT blind
spot => silence does not cover flights). Also {coverage_classes:[{class,
domain, label, monitored_in, not_monitored_in, via, statement}]} — per KIND
of disruption (on-track incidents and local rail operations, individual
flight delays, local road closures, country-level weather warnings…) where
it is observable to us and where NO configured source watches it, so "your
train was stopped by an incident only a local blog reported" is explainable
— plus {sources_consulted, sources_pending} per destination.
`since` optionally scopes the recheck window. Id is regex-validated;
unknown -> {"error": "not_found"}, malformed -> {"error": "invalid_trip_id"}.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | ||
| trip_id | Yes |