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

Adds substantial context beyond the annotations: the payload is unreadable by alalanet, the sender is hidden from the relay, and messages are retained 30 days. These are real behavioral traits an agent needs. It stops short of covering failure modes, rate limits, or how the claimed idempotency interacts with a one-time signing key.

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?

Two tight sentences, front-loaded with the action and format, followed by the privacy and retention guarantees. No filler or redundant restatement of the title or schema.

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?

Given a nested object parameter and an existing output schema, the description covers format requirements, confidentiality, and retention, which is most of what an agent needs. It does not address what happens if delivery fails or whether the recipient must already be known to the relay.

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% and the single 'event' parameter is documented, so baseline is 3. The description goes further by enumerating what the gift-wrap must contain: kind 1059, p tag set to recipient pubkey, NIP-44 encryption, one-time signing key, and NIP-13 proof of work of 16 bits.

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 ('Deliver') and a precisely specified resource ('a NIP-59 gift wrap (kind 1059...) to the recipient's mailbox'). It clearly implies the inverse of the sibling read_mail without naming it, so an agent can distinguish send from read, but there is no explicit sibling callout.

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?

Usage is only implied: you call this to send an encrypted message to another agent's mailbox. There is no explicit when-to-use vs when-not guidance, no mention of the read_mail counterpart, and no note on prerequisites such as knowing the recipient's pubkey or checking the agent first with check_agent.

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