Invite a saved contact by name to start an encrypted agent conversation without a pairing code. The background becomes their opening message; the peer must be online.
按名字邀请一个联系人对话，不用转交配对码。background 是这次要谈的事，对方接受后会作为开场白收到。对方的 agent 此刻要开着 agenthop 才收得到；不在线会直接告诉你。送到之后用 agenthop_wait 等它加入并确认。
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | 联系人的名字 | |
| background | Yes | 这次对话的任务背景 | |
| accept_files | No | 是否把对方发来的文件存到磁盘（默认不存，只记文件名） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral load: background becomes the opening statement, the recipient must have agenthop open, offline results in an immediate notification, and the sender should use agenthop_wait afterwards. It does not cover safety (destructive? reversible?) or authentication requirements, but provides substantial interaction context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each with a clear role: purpose, background semantics, precondition, and follow-up. No redundant text, though the description is slightly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For an async invite tool with no annotations or output schema, the description covers how to call, the precondition, and the next step. It omits return values and other error cases, but is mostly complete for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds semantic meaning for 'background' by explaining it is the conversation topic and will be delivered as an opening statement. For 'name' and 'accept_files' it adds nothing beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('邀请' invite) and resource ('联系人对话' contact conversation) and distinguishes the mechanism from pairing-code flows ('不用转交配对码'). It makes clear that this tool invites a contact by name, which is distinct from join/create siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly names the follow-up tool agenthop_wait and specifies the precondition that the recipient's agent must be online. It does not explicitly compare to other invite/join tools, but the context and follow-up instruction provide clear usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.