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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely useful behavioral context beyond them: the result is grouped by app with three count buckets, ordered by activity, and marked experimental. Missing only anything about pagination or size limits on the app list.

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?

Two sentences, zero filler, and the primary output shape (app list with three counts, most active first) is front-loaded before the parameter note. Nothing repeats the schema or annotations.

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 values need not be spelled out, and the description still summarizes the shape. With one optional param and full annotation coverage, the only real omission is how this differs from the adjacent recent_notifications tool.

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% and the single `since` parameter is an untyped anyOf(string, null) with no description, so the description carries the full burden. It does so precisely: ISO or unix seconds, and the default of 'everything kept', which is exactly what an agent needs to format the arg and know it is optional.

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 resource and verb-like behavior: apps that posted notifications, aggregated with counts of shown/hidden/unknown and sorted most-active-first. It is distinct from recent_notifications by being an aggregate-by-app view, though it never names that sibling to make the distinction explicit.

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?

Usage is only implied: an agent can infer this is for seeing which apps are chattiest, but the description gives no when-to-use vs when-not, and does not name recent_notifications or any alternative for drill-down. The 'Experimental' tag hints at caution but not selection guidance.

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