Read Notifications

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

With no annotations, the description carries the behavioral burden and discloses ordering ('newest first'), the non-screen-touching read behavior, the safety-policy withholding of sensitive notifications, and the ongoing-notification condition. It stops short of stating required permissions or whether any state is modified beyond 'without touching the screen'.

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 front-loaded with the core read operation and return fields, then uses semicolons to add conditions compactly. Every sentence fragment carries useful information with no wasted text.

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?

An output schema exists, so return-value details are optional, and the description still names the returned fields. It covers ordering, filtering, limits, and safety withholding, but two optional input parameters (device and package) remain undocumented.

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 0%, so the description must compensate. It usefully documents include_ongoing, package_name, and limit (default 20, cap 30), but leaves device and package unexplained, and does not clarify how package differs from package_name.

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 states a specific verb and resource: reading current status-bar notifications. It adds scope and output fields (key, app, title, text, action labels) and distinguishes the read-only nature from siblings like dismiss_notification and notification_action by saying it does so 'without touching the screen'.

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 usage conditions: ongoing notifications require include_ongoing=true, package_name filters to one app, and banking/authenticator notifications are withheld under the safety policy. It does not explicitly name alternative tools or when not to use this one, which keeps it from a 5.

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