start_app

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

No annotations are provided, so the description bears the full burden of behavioral disclosure. 'Injects the harness' hints at side effects (running app processes, possibly leaving the app running until stop_app), but neither the injection side effects, the need to call stop_app afterward, nor any state implications are disclosed. For a stateful tool that starts a process, this is a significant gap.

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?

One short sentence, efficient with no waste, but the terse structure omits critical context (usage, side effects). This is under-specification rather than conciseness—the single sentence does not fully earn its brevity given the missing behavioral guidance.

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?

The tool starts a long-running app in test mode—a state-heavy action—yet provides no output schema, no annotations, and no guidance on lifecycle expectations (how to stop, what happens to state, whether it blocks). Given 26 siblings forming an app-testing workflow, the description should clarify that start_app is the workflow entry point, which it does not.

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 parameters (project_path, device_id) are already documented in the schema. Baseline is 3. The description adds no parameter-specific detail beyond the schema, so it neither enhances nor degrades the parameter understanding.

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 verb ('injects the harness and starts') plus a clear resource ('the Flutter app in test mode'). It distinguishes reasonably from siblings like stop_app and pilot_hot_restart by establishing the startup role, though it could more explicitly frame itself as the entry point among the device-control sibling tools.

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 description gives no guidance on when to use this tool versus alternatives. There is no mention of prerequisites like needing a device, running list_devices first, or that this must precede interaction tools like tap/enter_text. With 26+ siblings, usage context is notably absent.

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