event_inbox
shallowcom.sonarconnections/sonar-connections · Verify this server
The person's own conversations with people they have connected with at an event, and the last few lines of one of them. Use it for "any messages", "did Jo reply", "what did Dana say", "read my inbox". Called with no arguments it lists up to twenty threads, person-to-person ones first: each row carries the other person's FIRST NAME, the last line, when it landed, whether that line was the person's own, and how many they have not read. Called with `firstName` or `chatId` it returns the last few lines of that one conversation, oldest first, each line saying only whether it was theirs, what it said and when. It carries no phone number, no email address, no surname, no account id and no photo: those are not on this surface. IT READS ONLY THE CALLER'S OWN CONVERSATIONS and the server re-checks that on every call, so a conversation they are not in comes back refused with NOT_PARTICIPANT rather than empty. A `firstName` is matched against THEIR OWN THREADS ONLY: if two of them answer to it the reply is AMBIGUOUS_NAME and names neither, and you ask which one they mean rather than choosing. If none does it is NAME_NOT_IN_THREADS, and you say you cannot see a conversation with that person. SHOW FIRST NAMES AND READ THE LINES OUT AS GIVEN. Say only what the reply carries: never guess who somebody is, what they meant, whether they are still at the event, or what is in a thread this reply did not return. Reading a conversation MARKS IT READ for that person, exactly as opening it in the app or on the web does. It requires a personal connector token: a shared one cannot reach anybody's conversations at all.
1 trials · measured 2 days ago
event_inbox scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against com.sonarconnections/sonar-connections, 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/bddf5101-86a9-4c20-a8de-40af9e54d50f)