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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuine domain context beyond that: it defines what a knock contains (identity/context, message, fit rationale) and the status taxonomy (waiting/accepted/no answer), which is valuable for an unfamiliar domain term.

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?

A single front-loaded sentence that covers both the received and sent collections without wasted prose. The nested parentheticals make it slightly dense but every clause carries meaning.

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?

With zero params, complete annotations, and an output schema handling return values, the description only needs to convey scope. It does so by covering both collections and their statuses, leaving little an agent would need beyond pagination/ordering details.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. Schema coverage is 100% and no parameter explanation is needed.

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 clear verb (list) and resource (knocks), and scopes it to both received and sent knocks with their statuses. It doesn't explicitly name a sibling to differentiate from, but it is plainly distinct from action tools like knock or respond_knock.

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 — an agent infers this is the tool for reviewing one's knock inbox/outbox. No explicit when-to-use versus alternatives such as whats_waiting, list_follow_requests, or read_unread is given.

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