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

The annotations indicate destructive and non-idempotent, but the description does not elaborate on potential consequences beyond creation. It does mention optional scheduling and that the message goes to all users, which gives some transparency, but it omits warnings about irreversibility or immediate delivery impacts.

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?

The description is relatively long due to the necessary procedural detail for section_id and use_local_time, but it is well-structured and each sentence serves a purpose. It avoids redundant wording and front-loads the core purpose.

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?

The tool lacks an output schema, and the description does not mention what the tool returns (e.g., created broadcast id) or possible errors. It also does not discuss permissions. For a non-trivial action like broadcasting to all users, this omission is a gap, though the parameter guidance is strong.

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 has 100% coverage, and the description enriches it further with practical instructions. For example, it explains the timezone offset format for send_at, the resolution workflow for section_id, and the condition for setting use_local_time to true. This goes beyond the basic schema descriptions.

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?

The description clearly states the tool creates a push broadcast message sent to all shop app users, with optional scheduling and tap action. The verb 'creates' and resource 'push broadcast message' are specific, and the audience 'all shop app users' differentiates it from a single-user push notification.

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?

The description provides detailed guidance on parameter usage, such as the required procedure for resolving section_id via cms_list_cms_sections and cms_list_sections, the timezone handling for send_at, and the advanced use_local_time flag. However, it does not explicitly name the alternative shop_create_push_notification for single-user sends, though the 'broadcast' wording makes the distinction implicit.

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