app_current

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

With no annotations and no output schema, the description carries the full disclosure burden, yet four words do not say what format the result takes (package string, activity string, object), what happens on the home screen or when no app is foreground, or whether any permission is needed. It adds only minimal behavioral information.

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?

It is certainly terse and front-loads the key noun phrase, but the terseness crosses into under-specification: it is a fragment rather than a complete sentence stating what the tool does or returns.

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 zero-arg query tool with no annotations and no output schema, the description should at minimum state that it returns the current foreground package and activity and what the shape of that result is. It gestures at the content but leaves the return format and edge cases entirely unspecified.

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?

The tool takes zero parameters and the schema is trivially complete, so there is nothing for the description to clarify here. Baseline 4 applies.

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 phrase 'Foreground package and activity' names the exact resource and implies a read of the currently active app, but it is a noun fragment with no verb, so the agent must infer that the tool returns the current foreground package/activity rather than setting it. It is distinguishable from siblings like app_list or app_launch by implication only, not by any explicit 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 when-to-use guidance, no mention of alternatives such as app_list (installed apps) or observe (screen state), and no stated preconditions. The agent gets only a topic, not a routing rule.

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