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

The description adds substantial behavioral context beyond the annotations: bounces arrive as separate messages after the send tool reports success, it scans INBOX and Junk by default, and results distinguish permanent vs. temporary failures with implications for resending. This is far more than the readOnly/idempotent hints already convey.

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 long but every sentence earns its place: purpose, timing, default behavior, result interpretation, user-facing obligation, and sibling routing. It is front-loaded with the core purpose and then layers in actionable guidance without redundancy.

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 read-only tool with no output schema, the description is remarkably complete. It explains when to use it, what it scans, what the results mean, how to interpret permanent vs. temporary failures, and how to combine it with check_receipts. Nothing essential is missing for an agent to invoke it correctly.

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 description coverage is 100%, so the schema already documents all three parameters with defaults and examples. The description reinforces the defaults and explains why Junk is scanned, but it does not add significant new parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Find messages that came back undelivered.' It clearly distinguishes this tool from check_receipts by stating that this tool only finds failures, while check_receipts covers the positive delivery/read side.

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?

Explicit usage guidance is provided: 'USE THIS AFTER SENDING ANYTHING IMPORTANT, and whenever the user asks whether a message arrived.' It also gives a clear exclusion: if the user asks whether a message arrived rather than failed, call check_receipts as well. This is model behavior for routing an agent to the correct sibling.

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