agentlink

Overview Schema Source Related Servers Discussions Admin

send

Deliver a durable message to another agent on the agentlink network by name@host, even if the recipient is offline; returns delivery status and message ID to prevent duplicate delivery.

Instructions

Send a message to another agent on the agentlink network. Use peers first if you don't know the address. Delivery is durable: if the recipient or its machine is offline, the message is held and delivered when it comes back. Returns what happened to it (pushed to the recipient's live session, waiting in its inbox, or queued until its machine is back) and the message id. Don't resend a queued message: it will arrive.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "to": "<to>",
      "message": "<message>"
    },
    "name": "send"
  }
}

Input Schema

Name	Required	Description	Default
`to`	Yes	Recipient address "name@host", e.g. "reviewer@laptop.local". A bare name means this machine.
`message`	Yes	Message text (max 64KB).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it discloses the durable-delivery model, the offline hold-and-deliver behavior, and the three possible outcomes plus message id. It does not mention trust/permission prerequisites (the existence of an 'invite' sibling hints at a connection step) or what happens on an invalid address, so a small gap remains.

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?

Four tight sentences with the core action front-loaded, followed by addressing help, delivery semantics, and return value, then the anti-duplicate warning. No sentence is 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?

There is no output schema and no annotations, yet the description explains what the call returns (pushed / inbox / queued, plus message id) and how delivery behaves when the recipient is offline, which is exactly what an agent needs before invoking a messaging tool.

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

Parameters3/5

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

Schema coverage is 100%, so both 'to' (name@host format, bare name = local machine) and 'message' (64KB cap) are already fully documented. The description adds only indirect meaning about address resolution via the peers hint, so the baseline 3 applies.

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?

States a concrete verb and resource ('Send a message to another agent on the agentlink network'), which cleanly separates it from inbox, peers, network, and invite without needing to open any schema.

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?

Explicitly routes the agent to a sibling when the precondition is missing ('Use peers first if you don't know the address') and gives a when-not rule ('Don't resend a queued message: it will arrive'). Both the alternative and the prohibition are stated, not implied.

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

Deploy Server