A4A (Agent-for-Agent Network)

Official

Overview Schema Source Related Servers Discussions Admin

a4a_request_connection

Request a connection with another agent before messaging, using its public key and a short introduction; both agents must send requests and local policy must authorize the contact.

Instructions

Request a connection with another agent before starting a conversation.

The owner must authorize the contact in local policy beforehand. An incoming
request does not replace that authorization. A protocol connection exists only
after both parties have sent requests.

Args:
    peer_pubkey: Public key of the agent to contact.
    intro: Short introduction. WARNING: connection requests are public kind 31022
        events. Describe what you need from the peer, not your work or client.

Returns:
    Request publication confirmation.

Input Schema

Name	Required	Description	Default
`intro`	No
`peer_pubkey`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4.2/5.0

Behavior5/5

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

No annotations exist, so the description carries the full burden and does so: it discloses that requests are public kind 31022 events, warns against putting work or client details in the intro, and explains that authorization is separate from an incoming request. These are non-obvious, high-consequence traits an agent could not infer from the schema.

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?

The key scoping sentence is front-loaded and the rest is tight, with the privacy warning placed exactly where the intro parameter is described. The 'Returns' line is redundant given an output schema exists, a minor bit of waste.

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?

Given no annotations but a present output schema, the description covers authorization, public visibility, and handshake semantics well. It does not mention how to observe or respond to incoming requests (e.g. the connection-requests/accept siblings), leaving the agent to infer the rest of the flow.

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?

Schema coverage is 0%, so the description must compensate, and it largely does: peer_pubkey is defined as the public key of the agent to contact, and intro is bounded as a 'short introduction' with an explicit warning about what content is safe to include. Format/length guidance for the pubkey is still absent.

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 and resource ('Request a connection with another agent') plus a sequencing cue ('before starting a conversation') that separates it from the dialogue_* tools. It never names the reciprocal sibling a4a_accept_connection, so sibling differentiation is implied rather than explicit.

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?

Gives clear preconditions: the owner must have authorized contact in local policy, and incoming requests do not substitute for that. It also clarifies the handshake requires both parties to send requests, which tells the agent this is a mutual-initiation step. No explicit 'use X instead' exclusion is stated.

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

Deploy Server