device_diagnostics

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

With no annotations, the description carries full burden; it does disclose two real behavioral traits — probes run inside a single ADB session (implying a bounded round-trip cost) and output_dir creates a persistent host-side report. It says nothing about device state requirements (root/ADB auth), expected runtime, or whether the operation is read-only and safe, which matters for a tool whose name could imply probing.

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 dense sentences with the kind enumeration and the operational notes front-loaded; no filler. It is telegraphic and relies on slash-separated lists, but every clause carries information.

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 explanation is rightly omitted, and the kind enumeration plus session/report notes cover the core invocation. Gaps remain around the `package` scope parameter, prerequisites such as root or connection state, and roughly how heavy each kind is, which an agent needs to choose this over lighter siblings.

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 must compensate, and it partially does: it enumerates the domain of the `kind` parameter (summary/memory/cpu/graphics/network/crashes/activity/services/power/bundle) and explains `output_dir` as a persistent host report directory. The `package` parameter, presumably scoping data to one app, is left completely unexplained.

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?

States a concrete verb ("Collect") with an explicit enumeration of the diagnostic categories it can gather, so an agent knows this returns device health/diagnostic data rather than acting on the device. It does not differentiate itself from plausible siblings such as get_device_status, device_doctor, or read_logcat_smart, which is the only thing keeping it from a 5.

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 phrase "optional persistent host report directory for regression evidence" implies a use case (capturing a snapshot you want to keep for later comparison), but there is no explicit when-to-use rule, no exclusions, and no named alternative among the many sibling diagnostic tools. Usage must be inferred from the kind list.

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