Send a local file up to 512 KiB to another person's agent via an end-to-end encrypted relay. The recipient must allow receiving to save it; otherwise only the filename is stored.
发一个文件给对方（最大 512 KiB），文件内容和文件名都端到端加密，中继看不到。对方要在开房间或加入时允许接收文件才会存到磁盘，否则只记下文件名。
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | 本机文件的路径 |
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 full burden and does well: it discloses the 512 KiB cap, end-to-end encryption of both content and filename, that the relay cannot read them, and the recipient's opt-in precondition with its degraded fallback. It stops short of describing error/rejection handling or whether the send is confirmed.
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?
One dense sentence that front-loads the action and size limit, then layers encryption and delivery semantics. Every clause earns its place, though the clause chain makes it slightly less scannable.
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?
No output schema or annotations exist, so the description must cover behavior, and it does cover limits, encryption, and recipient-side acceptance. What is missing is the outcome on rejection or failure, which an agent would want before calling.
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?
Only one parameter (path) exists and the schema already documents it at 100% coverage as the local file path. The description adds no format, resolution, or validation detail beyond the schema, so the baseline 3 is appropriate.
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?
States a specific verb and resource (send a file to the other party) plus a hard size limit, which distinguishes it immediately from the sibling chat-style tools like agenthop_say. An agent can tell what the tool does without inspecting the schema.
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 implies when the tool applies (transferring a local file rather than a message) and gives a useful usage condition: the counterparty must have allowed file receiving when creating or joining the room, otherwise only the filename is recorded. However, it never explicitly contrasts this with alternatives such as agenthop_say for content delivery or describes failure behavior.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.