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

Beyond the annotations (idempotentHint=true, destructiveHint=false), the description discloses the operational consequence of each value (warm-up bypass vs re-enabled), the cross-project scope of the setting, the eligibility precondition, and the exact two-step approval protocol including the {error:'approval_required', approval_token, summary} response. This is rich behavioral context that the structured fields do not carry.

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-loads the core action and its value semantics before moving to scope, precondition, and guardrails. Dense but each sentence carries non-redundant information; the guardrail sentence is slightly redundant with the 'no more than dashboard' framing but still 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 stateful mutation tool with no output schema, the description covers the effect, scope, eligibility, approval handshake, and safety framing. An agent can invoke it correctly on the first try; only the exact semantics of re-enabling warm-up timing (does it reset progress?) is left unstated.

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 schema already describes app_id and approval_token (67% coverage), and the description supplies the missing semantics for the 'on' boolean by spelling out the true/false behavior. It adds meaning beyond the schema for the required parameter, though it does not restate parameter formats.

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 verb+resource ('Mark the project's mailbox established') and immediately defines what both values of the boolean do ('true: no warm-up...false: the warm-up applies again'). It also clarifies scope ('It belongs to the mailbox, so every project sending from it follows'), which distinguishes it from sibling tools like set_project_mailbox and unlink_project_mailbox.

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?

Provides a clear precondition ('Only for a mailbox with a sending history') and gates the call via the approval-token flow, so an agent knows the setup required. It does not explicitly name an alternative sibling tool or state when-not to use it, keeping it short of a 5.

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