app_start

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

Annotations declare no readOnlyHint and idempotentHint=false, so mutation expectations are covered. Description adds meaningful behavioral context: the scrcpy fast path when session active vs ADB fallback, force-stop prefix behavior, and the explicit preference over manual UI navigation. No contradiction with annotations.

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, dense with useful information (purpose, preference, mechanism, fallback, force-stop option). No wasted words. Slight density reduction would bump to 5, but current structure earns every sentence.

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 launch operation with comprehensive annotations and schema, the description covers the core behavioral story: when to use, how it executes, and the force-stop variant. The aliasing of package/packageName is handled by the schema. Not exhaustive about failure cases or return values, but the output schema exists and annotations are solid.

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 100% with the packageName parameter already described including the '+' force-stop prefix syntax. The description's mention of the force-stop prefix (+) is useful and reinforces the schema, but adds little beyond what packageName's description already documents. Baseline 3 is appropriate when schema carries the weight.

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?

Clear verb+resource: 'Launch an app by package name.' Distinguishes from sibling app_stop (which does the opposite) and app_list/app_current (query tools). Explicitly contrasts with swiping the app drawer / manual UI navigation, establishing what this tool does better than alternatives.

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?

Explicitly states when to use: PREFERRED over swiping app drawer/manual navigation. Communicates the fast scrcpy path when a session is active with a fallback to ADB am start. Mentions the force-stop prefix (+) option. This tells the agent when and why this tool beats alternatives like tap/swipe.

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