notification_request_create

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

Beyond the annotations (which only say it's a non-read, non-idempotent write), the description discloses that it creates a draft rather than an active request, and explains the activation behavior tied to autosend. It also tells the caller what the response returns (requestId plus per-receiver notificationIds), adding return-value context not present in structured fields.

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 focused sentences, front-loaded with purpose, and every sentence adds workflow or return-value information. No filler or repetition of schema details.

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 high-complexity tool with a large nested schema and minimal schema descriptions, the description gives the essential workflow context (first call, no prerequisites, autosend choice, response shape). However, it omits details about the required `language` and provider/`data` structure, so it's not fully complete on its own.

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 only 17%, and the large nested `data` object is not described. The description does add useful semantics for `autosend` (immediate send on first batch activation or add receivers/documents before sending) and mentions inline receivers, but it does not compensate for the many undocumented parameters like `language`, `content`, `metadata`, or the provider-specific objects.

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 opens with a specific verb ('Creates') and resource ('notification request (draft)'), framing it as the top-level container in the certified-notification flow. It explicitly positions the tool as the first step, distinguishing it from sibling tools like notification_receiver_add, notification_document_add, and notification_request_send.

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?

It states 'Use this first, before any other Notification-manager tool' and 'No prerequisites,' giving explicit temporal placement. The autosend guidance explains when to set true vs false and directs the agent to call notification_request_send for the manual path, which contrasts with the sibling send tool.

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