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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=false. The description goes beyond them by disclosing what actually gets discarded ('cancel pending deliveries') and requiring user confirmation, which is the operationally important detail an agent needs before invoking.

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 short sentences, front-loaded with the action and effect, then the safety precondition. No filler or restated metadata.

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 rich annotations, an output schema, and full schema coverage, the description only needs to add behavioral context — which it does via the pending-delivery cancellation and the confirmation requirement. Minor gap: no note on whether disabling is reversible or how to re-enable the webhook.

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 itself explains reason/account_id usage and the authorization constraint. The description adds nothing about parameters, so the baseline 3 applies when structured fields carry the full load.

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+resource ('Disable the mailbox webhook') and adds the effect on pending deliveries. The verb 'disable' also usefully disambiguates from the tool's own name 'delete', implying the webhook config is preserved rather than destroyed. However, it doesn't explicitly differentiate from siblings like mailbox_email_webhook_set, which is the natural alternative.

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?

'Confirm with the user first' gives a real usage precondition, which is meaningful for a destructive call. It stops short of naming when-not-to-use it or pointing at the alternative (webhook_set to modify rather than disable), so guidance is implied rather than explicit.

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