startAssistantTool
shallowio.github.Avi-ADAM/1lev1 · Verify this server
Open the person's living list of (a) their PROFILE - skills, roles, ways of working, values, resources they own - seeded from what is on it now, plus what `text` says about them (pass what they told you); or (b) a WISH - pass ratsonId (from listMyWishesTool), or `text` to start a new draft wish from their words. Returns the rows with keys. Then refine with setAssistantItems (your own ops - preferred) or reviseAssistant (their words), and save with applyAssistant. A rikma is not started here: use proposeRikmaBlueprint. Docs: https://1lev1.com/mcp#startAssistantTool
1 trials · measured 2 days ago
startAssistantTool scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against io.github.Avi-ADAM/1lev1, measured 6 Oct 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
- self-provisionable
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-10-06 | 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/5ca5edf9-4d25-4171-b6b5-54510a6b4db7)