notify

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description adds genuinely new behavior beyond that: profile-supplied kind/title/icon/audio, waiting repeating until acknowledged, and prompt return with later delivery errors surfaced in list_notifications. Only minor gaps remain, such as whether repeats stop on timeout.

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 tight sentences, front-loaded with the primary action and mode, then behavior, then the error-surfacing caveat. No filler or restatement of the tool name.

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 an 8-parameter mutation tool with no output schema, it covers the async-return contract, error reporting path, and waiting lifecycle well; the main omission is explaining repeat_mode and the exact stopping condition for repeats.

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 coverage is 63%, so most parameters are documented structurally. The description adds the useful fact that a profile carries its own kind/title/icon/audio, but leaves repeat_mode's enum semantics and the interaction of sound/title vs. profile largely to 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 concrete verb and resource ("Show a local notification") and immediately distinguishes the two modes of specifying it (built-in kind vs. configured profile), routing the agent to the list_notification_profiles sibling for discovery.

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 gives clear context for the profile path (discover names via list_notification_profiles) and explains the waiting/repeat case, but never states when NOT to use this tool or how it relates to acknowledge_notification for stopping repeats.

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