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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety and repeatability are covered. The description adds genuine context beyond that: exactly what counts as an app (launcher icon, user and system alike), what is excluded (providers, accessibility services, Bluetooth stacks), and a concrete scale example (275 packages vs 23 apps). Return shape and pagination are not described.

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?

Three sentences, front-loaded with the core action before the inclusion/exclusion detail. The Pixel 275-vs-23 statistic is illustrative rather than filler, though it is the one element that could be trimmed without losing operational meaning.

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 read-only listing tool whose annotations already carry the safety profile and whose schema fully documents its three parameters, the description covers the key ambiguity (apps vs packages) and the effect of both flags. With no output schema, it could say more about what each returned entry contains, but nothing needed to invoke 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 100%, so both flags are already documented in the schema, which sets the baseline at 3. The description's "drop preinstalled apps" and "raw package list" phrasing largely restates the schema's "excluding preinstalled ones" and "packages with no launcher activity," adding only the framing that the two flags are opposing directions.

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 gives a specific verb and resource ("List the APPS installed on an Android device") and draws a sharp semantic line between apps and raw packages, which is the main source of confusion for this tool. It does not, however, explicitly distinguish itself from nearby siblings like app_list, ios_list_apps, or firebase_list_apps, so an agent must infer the device-vs-catalog split from the word "Android device".

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?

The sentence "Set userOnly to drop preinstalled apps, or includeNonLaunchable for the raw package list" gives conditional guidance for the two flags, which implies when each mode is appropriate. There is no explicit when-to-use versus alternatives such as app_list or ios_list_apps, so routing between siblings is left to inference.

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