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

With no annotations, the description fully discloses behavior: it is read-only, identical for every reader, contains no address in private rows, and includes guidance on how to seal a message. This goes far beyond the input schema and is highly transparent.

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?

The description is dense and front-loaded with the core purpose, followed by row structure and privacy implications. It is longer than strictly necessary, but every sentence adds valuable context, so no filler.

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?

For a parameterless read-only tool, the description completely covers what the agent needs: what the directory contains, the privacy model, the exact fields, the sealing SDK call, and the read-only nature. No output schema exists, but the description adequately describes the return format.

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 has zero parameters, so there is no parameter semantics to add. Baseline 4 is appropriate because the description does not need to compensate for any schema gaps.

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 clearly states the resource ('all published v2 mailbox rows') and the operation (fetching the directory). It explains the two row types and their fields, and distinguishes itself as an 'oblivious lookup' — making its purpose unambiguous and distinct from sibling message tools.

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?

The description gives clear context for when to use it: when you need to pick a recipient locally to avoid revealing intent. It does not explicitly name alternatives or state when not to use it, but the privacy-preserving rationale is enough to guide an agent.

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