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

Annotations already declare the mutation safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds genuinely non-obvious behavior: immutability of kind, rejection of active reminder/promotion mailers, the scheduling side effect, and hard rejection of timezone-designated datetimes. It does not cover permissions/authorization or whether omitted fields are left untouched versus cleared.

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?

Four compact sentences, front-loaded with the operation and its blockers, then the scheduling branch, then the timezone rule. The timezone sentence duplicates what the schema already states, which is the only wasted material.

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 15-parameter mutation with an output schema and full schema coverage, the description supplies exactly the cross-cutting rules an agent cannot infer from fields alone (kind immutability, kind-based update eligibility, scheduling vs editing). It omits kind-specific field validity (e.g., which fields apply to which mailer kind) and failure modes when constraints are violated.

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%, so the schema already documents all 15 parameters, including scheduled_at's naked-local-datetime rule and location_id's checkin_notification-only scope. The description's datetime guidance largely restates the schema's own scheduled_at description, adding emphasis rather than new meaning; baseline 3 applies.

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 ("Update an existing mailer") and immediately narrows scope with two hard constraints: the kind is immutable and active reminder/promotion mailers cannot be updated. It is clearly distinguishable from create_mailer, duplicate_mailer, and delete_mailer, though it never names those siblings 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?

Gives explicit when-not conditions (active reminder/promotion mailers) and explains the scheduled_at alternative path (schedule delivery instead of editing), which is the key branch an agent must get right. It stops short of routing to named alternatives such as deactivate_mailer or update_notification_schedule when the block applies.

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