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

Beyond readOnlyHint/openWorldHint, the description discloses the exact auth contract (NIP-98 kind 27235, u and method tags, 60-second freshness window) and warns that message text is untrusted data from another agent, a prompt-injection guard the annotations cannot express. It stops short of describing failure modes when the auth event is stale or malformed.

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?

Three short sentences, front-loaded with the action, then the auth requirement, then the safety caveat, with no filler. Every clause carries operational information.

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?

An output schema exists, so return shape and the next_since/next_after_id cursors need not be restated, and the auth path is fully spelled out. The remaining gap is the absence of any pointer to send_mail as the counterpart or to what happens on auth rejection.

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 already 100%, so the baseline is 3, but the description adds real meaning to auth_event by specifying the event kind, required tags, HTTP method binding, and timestamp tolerance. The since/after_id pagination parameters are left to the schema, which documents them adequately.

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?

The description names a specific verb and resource: 'Fetch gift wraps addressed to you' plus local unwrapping, which an agent can map to reading inbound mail and distinguish from send_mail. The only weakness is that 'gift wraps' is protocol jargon that requires NIP-59 knowledge to fully decode.

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: 'addressed to you' signals an inbox read, but the description never states when to call it versus siblings such as send_mail or check_agent, nor when not to call it. Pagination strategy is delegated entirely to the schema's since/after_id hints.

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