mcp-agent-hub

read_inbox

Retrieve agent inbox messages, including direct, broadcast and room messages. Filter by unread status, message type, task ID, room or sender to find relevant coordination updates.

Instructions

读取收件箱。默认返回发给自己、广播和已加入房间的消息。unread_only=true 只看未读；kinds 可过滤消息类型；task_id 可只看某任务相关。

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": "read_inbox"
  }
}

Input Schema

Name	Required	Description	Default
`room`	No
`agent`	No
`kinds`	No
`limit`	No
`task_id`	No
`since_id`	No
`unread_only`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 27, 2026

TDQS

B3.3/5.0

Behavior3/5

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

No annotations are provided, so the description carries the burden. '读取' signals a read-only operation and the default-scope sentence is genuinely useful behavioral detail (what comes back without filters), but pagination/ordering via limit and since_id, and whether results are capped or de-duplicated, are unstated.

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?

Three compact sentences, front-loaded with the purpose then filter behavior. No filler, though the filter enumeration reads as a single dense run-on rather than being grouped by relevance.

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

Completeness4/5

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

Output schema exists so return values needn't be described, and the default-scope sentence plus three filter explanations cover the core call pattern. The gap is the four undocumented parameters, particularly since_id/limit for incremental polling.

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

Parameters2/5

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

Schema description coverage is 0%, so 7 parameters are bare titles. The description explains only unread_only, kinds, and task_id; room, agent, limit, and since_id — including the important since_id polling semantics — are left completely undocumented.

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

Purpose4/5

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

States a specific verb+resource ('读取收件箱') and clarifies the default scope: messages to self, broadcasts, and joined rooms. It distinguishes the tool from write-oriented siblings like mark_read and send_message, though it never names them.

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

Usage Guidelines3/5

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

Implied usage only — it explains what the filters do (unread_only, kinds, task_id) but never says when to choose this tool over mark_read or activity_log, nor any preconditions. An agent can infer polling use from the filters but must guess at alternatives.

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