hunchful

Relay: inbox status and consent

relay_status

Read-onlyIdempotent

Start here for messaging. Hunchful relay lets people talk to friends — usually through their agents. Returns unread counts, conversations, pending drafts, the person's friend code, and the CONSENT POLICY you must stay within (per audience: off / draft = you write, the person sends / send). Also returns the relay rules — read them.

RULES: You are relaying messages between real people. Speak for your person only within the consent they set (relay_status → policy); never widen it. Messages are NOT end-to-end encrypted — Hunchful can read them for safety. Never send ID numbers, passwords/PINs, bank or card details, health details, or anyone else's private information. Tell your person the same if they try. Every message you send is labelled as written by an agent. Never pretend to be your person typing. FLAG (call flag_conversation, stop sending in that conversation, and tell your person plainly) when you see: threats or intimidation; any sexual content involving someone who may be a minor; grooming (secrecy requests, isolating, pushing for images); extortion or blackmail; scams or requests for money, gift cards or crypto; someone at risk of self-harm (also point your person to local emergency help); pressure to move off-platform or delete messages to avoid oversight; repeated contact after a clear no. Do NOT flag: disagreement, awkwardness, bluntness, a single rude message, loneliness, unusual interests, or someone simply being different. People here are often lonely — be kind, not suspicious. When unsure, ask your person rather than flagging. Never argue with or confront the other side about a flag, and never tell them you flagged. Summarize incoming messages faithfully; don't invent or soften what the other person said. Strangers: someone under an alias has not chosen to be known — never try to work out who they are, and never reveal your person for them; revealing is each person's own choice in the web inbox. Group chats: speak there only if the person's 'groups' policy allows it and they asked you to; you are one voice among several people — be brief, never speak for other members, and never flag a group member for merely disagreeing. Knock on someone new only when your person asked to meet people and approved the wording. Be honest about who they are or why they're reaching out. A decline (or silence) is an answer — don't knock again.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description	Default
`me`	Yes
`rules`	Yes
`groups`	Yes
`listed`	Yes
`policy`	Yes
`unread`	Yes
`guidance`	Yes
`inboxUrl`	Yes
`friendCode`	Yes
`restriction`	Yes
`friendsCount`	Yes
`conversations`	Yes
`draftsPending`	Yes
`knocksWaiting`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 16, 2026
- addedOutput schema / properties / policy / properties / places
```
Added value: +{
+  "$ref": "#/properties/policy/properties/friends"
+}
```
- addedOutput schema / properties / policy / properties / professional
```
Added value: +{
+  "$ref": "#/properties/policy/properties/friends"
+}
```

Changed2 schema fields changedSep 25, 2026

addedOutput schema / properties / groups

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "conversationId": {
+        "type": "string"
+      },
+      "groupId": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "groupId",
+      "name",
+      "conversationId"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "me",
-  "unread",
-  "policy",
-  "friendCode",
-  "conversations",
-  "friendsCount",
-  "draftsPending",
-  "knocksWaiting",
-  "listed",
-  "restriction",
-  "inboxUrl",
-  "rules",
-  "guidance"
-]New value: +[
+  "me",
+  "unread",
+  "policy",
+  "friendCode",
+  "conversations",
+  "friendsCount",
+  "draftsPending",
+  "knocksWaiting",
+  "listed",
+  "groups",
+  "restriction",
+  "inboxUrl",
+  "rules",
+  "guidance"
+]

Changed7 schema fields changedSep 25, 2026

addedOutput schema / properties / conversations / items / properties / iRevealed
```
Added value: +{
+  "type": "boolean"
+}
```

changedOutput schema / properties / conversations / items / required

Previous value: -[
-  "conversationId",
-  "kind",
-  "with",
-  "lastMessageAt",
-  "lastPreview",
-  "lastFromMe",
-  "unread",
-  "closed",
-  "agentPaused"
-]New value: +[
+  "conversationId",
+  "kind",
+  "with",
+  "iRevealed",
+  "lastMessageAt",
+  "lastPreview",
+  "lastFromMe",
+  "unread",
+  "closed",
+  "agentPaused"
+]

addedOutput schema / properties / knocksWaiting
```
Added value: +{
+  "type": "number"
+}
```
addedOutput schema / properties / listed
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / me / properties / anonymous
```
Added value: +{
+  "type": "boolean"
+}
```

changedOutput schema / properties / me / required

Previous value: -[
-  "uid",
-  "name"
-]New value: +[
+  "name"
+]

changedOutput schema / required

Previous value: -[
-  "me",
-  "unread",
-  "policy",
-  "friendCode",
-  "conversations",
-  "friendsCount",
-  "draftsPending",
-  "restriction",
-  "inboxUrl",
-  "rules",
-  "guidance"
-]New value: +[
+  "me",
+  "unread",
+  "policy",
+  "friendCode",
+  "conversations",
+  "friendsCount",
+  "draftsPending",
+  "knocksWaiting",
+  "listed",
+  "restriction",
+  "inboxUrl",
+  "rules",
+  "guidance"
+]

AddedSep 25, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: that messages are NOT end-to-end encrypted, that every outgoing message is labelled as agent-written, that consent is per-audience (off/draft/send), and how abuse escalation should work. This is far richer than the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and return contents are front-loaded before the RULES block, and headers make it skimmable. It is long, however, and a meaningful portion of the rules (knock etiquette, group-chat conduct) governs sibling tools rather than this one, so not every sentence is tightly scoped to relay_status.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema exists and the description still previews the key returns, while supplying the consent-policy and safety semantics that no structured field could express. An agent has everything needed to call it and to interpret the consent values it receives.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline of 4 applies; there is nothing in the schema for the description to elaborate on. It does usefully announce what the call returns, including the consent policy, which is the main semantic payload.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a specific verb+resource ('relay lets people talk to friends', 'returns unread counts, conversations, pending drafts, the person's friend code, and the CONSENT POLICY') and explicitly positions itself as the entry point ('Start here for messaging'), which distinguishes it from siblings like list_conversations, read_unread and whoami that cover subsets of the same data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use ('Start here for messaging'), routes to the alternative when relevant ('call flag_conversation, stop sending in that conversation'), and gives both when-to-flag and when-NOT-to-flag criteria ('Do NOT flag: disagreement, awkwardness, bluntness...'). Selection and downstream behavior are fully specified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All hunchful tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.