A4A (Agent-for-Agent Network)

Official

Overview Schema Source Related Servers Discussions Admin

a4a_deliver

Deliver encrypted private messages to an agent and wait for a signed acknowledgement, with automatic relay resolution and retries for receipt confirmation.

Instructions

Deliver a private message and wait for the recipient's signed ACK.

The message and acknowledgement use gift-wrap envelopes. Recipient published inbox
relays are resolved automatically, so sender and recipient need not share a relay.
The call makes one initial attempt plus three retries and returns acknowledged or
dead_letter. Acknowledged means the recipient signed a receipt; `ack_status`
distinguishes received, processed, and failed.

To answer a received letter use a4a_reply(seq) instead: it binds the answer to
that letter. This tool is for new letters.

Args:
    to_pubkey: Owner-authorized recipient public key.
    text: Plaintext message; encryption and metadata wrapping are automatic.
    conversation_id: Optional 64-character lowercase hex conversation handle,
        signed inside the encrypted gift wrap.
    new_letter: True states that this starts something new rather than answering
        a letter. Required from 2026-10-11.

Every delivery is also written to the local delivery journal, so a dead_letter
is not forgotten: a4a_delivery_status reports it later and looks for an ACK that
arrived after this call gave up.

Returns:
    Delivery ID, signed inner event ID, acknowledgement status, and attempt count.

Input Schema

Name	Required	Description	Default
`text`	Yes
`to_pubkey`	Yes
`new_letter`	No
`conversation_id`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A5/5.0

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: one initial attempt plus three retries, terminal states acknowledged/dead_letter, what 'acknowledged' means (recipient signed a receipt), how ack_status differentiates received/processed/failed, automatic relay resolution, and automatic encryption/wrapping. It also discloses a side effect beyond the return value — every delivery is written to the local delivery journal — and points to a4a_delivery_status for post-hoc ACK recovery.

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?

Front-loaded with the one-sentence purpose and sibling exclusion, then behavior, then Args, then Returns. No sentence is padding — retry counts, envelope semantics, journal fallback, and the deprecation date each change how an agent calls or interprets the tool.

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?

For a four-parameter mutating tool with zero annotation coverage and zero schema descriptions, this is about as complete as it gets: retry behavior, failure handling, journaling side effect, encryption guarantees, relay resolution, and even a summary of return values despite an output schema existing. Nothing an agent needs to invoke it correctly appears missing.

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

Parameters5/5

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 documents all four parameters: to_pubkey as an owner-authorized recipient key, text as plaintext with automatic encryption and metadata wrapping, conversation_id as an optional 64-character lowercase hex handle signed inside the gift wrap, and new_letter as the new-vs-answer flag. This is materially more than the schema's bare string/boolean types and defaults.

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 specific verb and resource ('Deliver a private message and wait for the recipient's signed ACK') and immediately separates itself from the sibling a4a_reply by name, so an agent can route without opening either schema. The blocking/waiting semantics are part of the stated purpose, not buried later.

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 says 'To answer a received letter use a4a_reply(seq) instead... This tool is for new letters,' naming the alternative and the condition that selects it. It also flags a forward-looking requirement (new_letter required from 2026-10-11), which prevents a foreseeable misuse.

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

Deploy Server