Skip to main content
Glama

inbox

Read-onlyIdempotent

Preview unread Nexus Relay messages to identify requests that still need a full read before replying; handled replies and replies awaited by another session are not listed.

Instructions

Your unread messages (preview); read(id) reads one in full. Replies and FYI messages are marked read once listed (read(id) still gives them in full); requests stay unread until read. Replies another session is waiting for (wait_reply) are not listed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "inbox"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
noteYes
errorNo
hiddenNo
statusYes
unreadYes
late_noteNo
late_repliesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv1.8.7
    • addedOutput schema / $defs
      Added value: +{
      +  "Attachment": {
      +    "properties": {
      +      "mime": {
      +        "title": "Mime",
      +        "type": "string"
      +      },
      +      "name": {
      +        "title": "Name",
      +        "type": "string"
      +      },
      +      "path": {
      +        "title": "Path",
      +        "type": "string"
      +      },
      +      "size": {
      +        "title": "Size",
      +        "type": "integer"
      +      }
      +    },
      +    "title": "Attachment",
      +    "type": "object"
      +  },
      +  "RenderedMessage": {
      +    "properties": {
      +      "attachments": {
      +        "items": {
      +          "$ref": "#/$defs/Attachment"
      +        },
      +        "title": "Attachments",
      +        "type": "array"
      +      },
      +      "cancelled": {
      +        "title": "Cancelled",
      +        "type": "string"
      +      },
      +      "created": {
      +        "title": "Created",
      +        "type": "string"
      +      },
      +      "due": {
      +        "title": "Due",
      +        "type": "string"
      +      },
      +      "from": {
      +        "title": "From",
      +        "type": "string"
      +      },
      +      "id": {
      +        "title": "Id",
      +        "type": "string"
      +      },
      +      "info": {
      +        "title": "Info",
      +        "type": "boolean"
      +      },
      +      "quality": {
      +        "title": "Quality",
      +        "type": "string"
      +      },
      +      "reply_to": {
      +        "title": "Reply To",
      +        "type": "string"
      +      },
      +      "state": {
      +        "title": "State",
      +        "type": "string"
      +      },
      +      "text": {
      +        "title": "Text",
      +        "type": "string"
      +      },
      +      "to": {
      +        "title": "To",
      +        "type": "string"
      +      },
      +      "topic": {
      +        "title": "Topic",
      +        "type": "string"
      +      },
      +      "vote": {
      +        "title": "Vote",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "id",
      +      "from",
      +      "to",
      +      "topic",
      +      "created",
      +      "text"
      +    ],
      +    "title": "RenderedMessage",
      +    "type": "object"
      +  }
      +}
    • addedOutput schema / properties / error
      Added value: +{
      +  "title": "Error",
      +  "type": "string"
      +}
    • addedOutput schema / properties / hidden
      Added value: +{
      +  "title": "Hidden",
      +  "type": "string"
      +}
    • addedOutput schema / properties / late_note
      Added value: +{
      +  "title": "Late Note",
      +  "type": "string"
      +}
    • addedOutput schema / properties / late_replies
      Added value: +{
      +  "items": {
      +    "$ref": "#/$defs/RenderedMessage"
      +  },
      +  "title": "Late Replies",
      +  "type": "array"
      +}
    • addedOutput schema / properties / note
      Added value: +{
      +  "title": "Note",
      +  "type": "string"
      +}
    • removedOutput schema / properties / result
      Removed value: -{
      -  "title": "Result",
      -  "type": "string"
      -}
    • addedOutput schema / properties / status
      Added value: +{
      +  "const": "success",
      +  "title": "Status",
      +  "type": "string"
      +}
    • addedOutput schema / properties / unread
      Added value: +{
      +  "items": {
      +    "$ref": "#/$defs/RenderedMessage"
      +  },
      +  "title": "Unread",
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "result"
      -]New value: +[
      +  "status",
      +  "unread",
      +  "note"
      +]
    • changedOutput schema / title
      Previous value: -"inboxOutput"New value: +"InboxOut"
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior1/5

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

The annotations declare readOnlyHint=true, but the description says replies and FYI messages are marked read once listed, which is a state mutation and contradicts the read-only annotation. The extra detail about requests staying unread is useful, but the contradiction is serious.

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

Conciseness5/5

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

The purpose is front-loaded, and each subsequent clause adds a distinct behavioral detail: full-message reading, mark-read semantics, and wait_reply exclusion. There is no filler.

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?

Given the zero-parameter schema, existing output schema, and annotations, the description covers the important inbox-specific behavior: which messages are listed, which are marked read, which stay unread, and which are excluded for wait_reply. Enough context is provided to call and interpret the tool.

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 has zero parameters, so the schema does not need parameter explanation and the baseline is 4. The description appropriately focuses on listing behavior rather than input semantics.

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?

The description clearly states that this tool returns unread messages as a preview and distinguishes it from read(id) for full messages and wait_reply for replies another session is waiting on. An agent can identify the resource and scope without opening the schema.

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

Usage Guidelines4/5

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

It gives useful routing context: use read(id) to read one message in full, and wait_reply responses are not listed here. It does not explicitly compare against broader siblings such as search, summary, or status, so it is clear but not fully exhaustive.

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