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

Annotations already cover read-only safety, and the description layers on behavior the annotations cannot: the experimental dependency on an undocumented macOS database, retention past Notification Center, the tri-state `shown` semantics with concrete causes for hidden ones, and a prompt-injection warning about notification text being attacker-controlled. That is exactly the additive context this dimension rewards.

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?

Nearly every sentence is load-bearing and the core identity is front-loaded. It reads as one dense block where parameter details, the `shown` explanation, and the safety warning run together, so scanning costs more than it should, but there is very little filler to cut.

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 4-parameter read tool with an output schema, the description covers source, ordering, filtering semantics, pagination ceiling, and the one output field an agent must interpret ('shown') without redundantly restating return structure. Nothing needed to call it correctly is missing.

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%, so the description carries the full burden and does: `app` accepts a bundle id or app name with an example ('slack'), `since` accepts ISO or unix seconds, `include_hidden=false` drops known-hidden entries, and `limit` is bounded 1–200 with default 25. All four parameters gain meaning not present in the bare 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+resource and scope: notifications any app posted on this Mac, newest first, drawn from Keeploop's own copy of macOS notification history. That scope statement plus the retention detail ('keeps them after they leave Notification Center') clearly separates it from siblings like notification_apps and create_notification_monitor without needing to name them.

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 actionable narrowing guidance ('narrow `since` or `app` to see further back') and explains the include_hidden=false filtering condition, which is real when-to-use signal. It stops short of naming a sibling alternative or stating exclusions (e.g. when to use notification_apps instead), so it lands at 4 rather than 5.

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