inbox

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real value beyond them: results are previews, not full bodies, and the result set deliberately omits messages another session is awaiting. That is exactly the kind of set-composition detail an agent cannot infer.

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 compact sentences, front-loaded with what the agent gets, followed by the two exclusions that would otherwise cause misreads. No filler or restatement of the name.

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 need not be described, and the description covers the non-obvious filtering rules. What's missing is a note on bounding or truncation of the preview list, a minor gap for a zero-parameter listing tool.

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 to disambiguate and the baseline is 4. The mention of `read(id)` clarifies the sibling's signature rather than this one's, which is still useful context but adds nothing to this tool's own parameters.

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?

Names the resource (unread messages) and its scope (preview only) with a clear, agent-usable framing. It also differentiates from the sibling `read`, so the agent can pick between the two without opening schemas.

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?

Explicitly routes the agent to `read(id)` for full content and notes that replies pending in `wait_reply` are excluded, which prevents a wrong expectation. It stops short of stating a triggering condition (e.g., poll this first, then read), but the alternatives are named.

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