Read Notifications

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

Annotations are absent, so the description carries the full burden of behavioral disclosure. It only lists the output fields, giving no information about side effects, read-only nature (implied but not stated), any limits, filtering behavior, or what happens if no notifications exist. The description does not reveal whether include_ongoing affects results or how the device/package filters work.

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 a single sentence, which is concise, but it is effectively a list of fields rather than a structured explanation. It is not front-loaded with the tool's purpose or usage. The information it contains could be better organized, and it does not earn its place as a functional description.

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?

While an output schema exists (so return format is covered elsewhere), the tool has four parameters with no documentation, and the description doesn't address them. It also provides no usage context or behavioral details. For a basic read operation this is incomplete; an agent would struggle to customize the call 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?

Schema description coverage is 0%, and the description provides no explanation of the parameters (limit, device, package, include_ongoing). It lists only the return fields, so an agent cannot understand how to use the tool's arguments or their allowed values. This is a complete failure to compensate for the schema's lack of 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 'Notifications currently posted: key, app, title, text, action labels, clearable.' conveys that the tool reads/returns current notifications and lists the fields included, but it does not use an explicit verb like 'reads' or 'returns'. The name 'read_notifications' is clear, and the field list distinguishes it from action tools like dismiss_notification, but it lacks a precise functional statement.

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?

There is no guidance on when to use this tool versus alternatives such as get_screenshot, read_screen, or notification_action. No mention of prerequisites, context, or scenarios. The agent must infer usage purely from the name and field list, which is inadequate for making an informed choice.

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