get_wellness
shallowrun.stas/stas · Verify this server
Read all locally stored Intervals.icu wellness values for any requested date window; there is no fixed day cap and this read makes no live provider request. The response is column-oriented: dates[i] is the date for every series[field][i] and customSeries[field][i]. null means not recorded, never zero. Only fields with at least one value are returned. window=[oldest inclusive,newest exclusive]; missingRanges uses the same boundaries and names dates for which STAS has no stored wellness row. complete=true means the response is not truncated and includes all meaningful locally stored standard and custom wellness fields; it does not claim the watch/provider supplied every metric. source=intervals_icu_cached_by_stas means values may originate from a watch, another connected source, or manual Intervals.icu entry and are served from STAS cache. Interpret trends against this athlete's own baseline and together with workouts and reports; do not judge readiness or diagnose from one value. CTL is modeled longer-term training load, ATL shorter-term load, and CTL-ATL can be used as Form; higher or lower is not inherently good or bad. HRV is protocol/device dependent and is mainly useful relative to the athlete's own trend. Resting HR is also individual; acute deviation matters more than a universal threshold. sleepSecs is seconds. sleepQuality is 1=Excellent through 4=Poor. soreness/fatigue/stress are 0=None through 4=Extreme, higher is worse. mood/motivation are 1=Excellent through 4=Poor, higher is worse. providerUpdatedAt is the provider record update time, not the measurement time. Preserve custom field names exactly; if a custom field's unit or scale is unclear, do not invent it—describe only its observed trend or ask the user. If the complete response is too large, retry every exact non-overlapping window in suggestedWindows; if none are suggested, explain that one stored day itself cannot be split further by date. Never treat a partial window as the whole request.
1 trials · measured 8 days ago
get_wellness scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against run.stas/stas, measured 25 Aug 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- gated
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-08-25 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/fce257ff-9c49-4e17-b6bc-d2021b946747)