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

Annotations already carry readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes further with real operational detail: auth is required, inbox-scoped keys receive 403 permission_denied, and unauthorized failures are explicitly named. That is meaningful disclosure beyond the structured fields.

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?

Front-loaded with the usage trigger, then auth, then return shape and error modes in a tight sequence with no filler. Dense but each sentence carries distinct information; the inline return-shape block is a little compact to parse but not wasteful.

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 no output schema present, the description supplies the return envelope and field list, enumerates the reason values (bounce/complaint/manual), explains source_message_id including its null case, and covers auth failure modes. An agent has everything needed to call and interpret this 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?

This tool takes zero parameters, which sets the baseline at 4, and the description confirms it with 'Inputs: none.' There is no parameter surface to elaborate on, so nothing more is expected or missing.

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 a specific resource — the addresses the account will not email — and defines exactly what populates that list (permanent bounce, complaint, manual add). The read/list intent is unambiguous from the title and the 'addresses you need' framing, though it never explicitly routes against the sibling cooper_delete_suppression, so it stops short of a 5.

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?

Opens with an explicit 'Use this when you need...' trigger tied to a concrete situation (reviewing addresses that won't be emailed). It adds auth-scope exclusions (inbox-scoped keys rejected) but names no alternative tool for adjacent needs, so it is clear context without the full when/when-not/alternatives treatment.

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