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

Annotations already declare destructiveHint=true and idempotentHint=true, lowering the bar. The description still adds real behavioral context: which mailboxes get silently skipped and listed, and that patch only touches shared settings with no credentials. It does not describe partial-failure or return behavior, keeping it short of a 5.

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?

A single dense sentence that front-loads the core operation and packs the exclusivity rule, skip behavior, and sibling routing without a wasted clause. Every fragment earns its place.

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 destructive bulk mutation with no output schema, the description covers the key gaps: skip semantics, mode exclusivity, and credential scope. It leaves unspecified what a partial failure or the response payload looks like, which is a minor remaining gap given annotations carry the safety profile.

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?

Top-level schema coverage is 0% (ids, status, patch have no descriptions), so the description must compensate and largely does: it explains the status enum values, scopes patch to 'shared settings, no credentials', and enforces the mutual-exclusivity rule that the schema itself does not encode via oneOf. The ids array's cardinality is only implied, not restated.

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?

States a specific verb and resource ('Apply ONE change to up to 1000 mailboxes') and enumerates the two mutation modes (status vs patch). It also names the sibling resume_mailbox as the correct tool for failed/revoked/checking mailboxes, so an agent can separate this from update_mailbox and resume_mailbox 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?

Gives explicit when-to-use (bulk one-change across up to 1000 mailboxes), when-not (failed/revoked/checking mailboxes are skipped; use resume_mailbox instead), and the selection constraint ('Exactly one of the two'). The alternative tool is named, not implied.

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