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

The description discloses the read-modify-write behavior ('reads your current preferences, applies the overrides, and saves the full set back') and notes the return value. It also surfaces the prerequisite for slack/discord. Annotations already indicate this is not read-only or destructive, and the description adds specific merge semantics beyond that.

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?

Three concise sentences with no filler; the purpose is stated first, followed by usage and behavior. Each sentence contributes essential information, and the description is appropriately sized for a tool with one parameter.

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 tool with one nested parameter, the description covers the merge behavior, the channel prerequisites, and the return value. The schema and output schema fill in the field-level details, so an agent has everything needed to invoke it correctly.

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 each channel field, but the description adds crucial semantic information about the partial-override behavior and the fact that only specified events/channels are changed. This directly addresses the single 'preferences' parameter and clarifies how to use it, which is value beyond the schema.

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 and resource ('Change how you are notified for specific events') and clearly distinguishes from read-only retrieval by describing the override-and-save behavior. It also differentiates from channel configuration tools by noting the prerequisite with set_notification_channel.

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 gives explicit guidance on partial updates ('Pass only the events — and only the channels — you want to change') and explains the merge behavior that preserves untouched settings. It also states the prerequisite for slack/discord, but does not explicitly contrast with alternative tools like get_notification_preferences or set_notification_channel, so usage context is clear but not exhaustive.

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