homebutler

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

With no annotations provided, the description carries the full disclosure burden and successfully identifies the destructive scope (containers, config, volumes). It could improve by explicitly stating this operation is irreversible or requires caution.

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?

Single 12-word sentence with zero waste. Every clause earns its place: action verbs first, followed by specific destruction targets. Perfectly front-loaded and efficient.

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 single-parameter destructive operation without output schema or annotations, the description adequately covers the behavioral scope. Minor gap: lacks irreversibility warning expected for destructive tools.

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 input schema has 100% description coverage ('App name'), establishing a baseline of 3. The description provides no additional semantic context about valid app name formats, lookup behavior, or validation rules beyond the schema.

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 uses specific verbs ('Stop', 'delete') and clearly identifies the resource ('installed app') and scope of impact ('all data including containers, config, and volumes'). It effectively distinguishes from sibling install_uninstall by emphasizing complete data destruction.

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 provides implied usage context through the specificity of what gets destroyed (data/containers/volumes), suggesting this is for complete removal. However, it lacks explicit guidance on when to choose this over install_uninstall or prerequisites like requiring an installed app.

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