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

With no annotations, the description carries the full behavioral burden and delivers: free, non-destructive, unacked-only, body URL redeemability limits, TTL-based persistence, and pagination via next_cursor. This goes well beyond the structured schema.

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 sentences, front-loaded with cost/safety, and each clause adds distinct operational detail (body handling, retention, pagination). 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 tool with no output schema, it explains key return elements (body_b64, large-body URL, next_cursor) and lifecycle behavior. The main gap is that optional filtering and limit behavior are undocumented, but the tool remains callable from the required auth parameters.

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 description adds meaning to 'address' (your address), 'cursor' (next_cursor pagination), and clarifies the default unacked filter. However, with only 50% schema coverage, it leaves limit and the nested filter object (tag/since/producer) unexplained in both the schema and the description.

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?

Identifies a specific operation (returns unacked messages for the caller's address) and a specific resource (mailbox), with concrete output details (body_b64, signed body_url). The 'non-destructive' phrasing and explicit contrast with locker_ack make it distinguishable from sibling mail 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?

Explains the tool is for reading unacked messages and notes messages remain until explicitly acked or TTL expiry, which implies when to use locker_ack instead. It does not explicitly name sibling alternatives for counting or capability checks, but the context is clear enough for selection.

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