container_prune_tool

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

The description discloses the action (removing stopped containers) and the return value (list of IDs and reclaimed space), but with no annotations it does not mention that this is a permanent destructive action or irreversible. The behavioral disclosure is adequate but lacks depth about consequences or safety.

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?

The description is two sentences and front-loaded with the core action. Every word earns its place, and the return value is explained in a second concise sentence. No fluff or repetition.

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 tool with no parameters and a simple operation, the description is complete. It states the action and the response format, and the output schema covers structured return details. No prerequisites or additional context are needed.

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 has zero parameters, so the description adds no param-specific meaning. Baseline is 4 for tools with no parameters, and since the schema is empty and concise, this is appropriate.

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 the specific verb 'Remove' with the resource 'containers' and clearly scopes it to 'all stopped containers'. This distinguishes it from container_rm_tool (which removes specific containers) and image_prune_tool (which prunes images).

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 clearly states when to use the tool: to remove all stopped containers in one action. It does not explicitly list alternatives or when-not conditions, but the scope 'all stopped containers' provides clear context. The lack of exclusions or alternative references keeps it just below a 5.

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