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

Annotations already flag destructiveHint=true and openWorldHint=true, so the bar is lower, and the description still adds real substance: a wider rollout causes Aide to email customers 'from then on' (clarifying non-retroactivity) and 'sent emails can't be recalled' spells out the concrete irreversibility behind the destructive hint. It omits permission requirements and whether changes can be rolled back by resetting.

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 dense sentences with no filler; the resource and partial-update rule come first, followed by the risk warning. Every clause carries information an agent needs.

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 mutation tool with a nested rollout object and no output schema, the description covers the main risk and the patch semantics, which is what an agent needs before calling it. It leaves out permissions and return behavior, but the schema carries the field-level detail.

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%, and the schema already documents rollout modes, quietPeriodSeconds bounds, and reset paths in detail, so the baseline of 3 applies. The description only references 'quiet period' and rollout at a high level and never mentions the reset parameter.

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: changing who receives replies on a support mailbox plus its quiet period, and clarifies the partial-update semantics with 'only the fields given change.' It is clearly distinguishable from read-oriented siblings like get_support_email_settings, though it never names an alternative explicitly.

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?

Usage is implied by the mutation verb and the note that unspecified fields are preserved, but there is no explicit statement of when to use this versus get_support_email_settings (to inspect current values) or set_inbox_ai. No prerequisites or exclusions are given.

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