Docker Prune

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

With no annotations, the description carries the behavioral burden. It discloses that the default is a non-destructive dry-run and that actual deletion requires explicit flags. This is essential transparency for a destructive operation, though it does not mention irreversibility in words; 'real deletion' implies it.

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?

Two concise sentences, front-loaded with the default dry-run behavior, then the trigger for real deletion. There is zero filler; every word adds value.

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 low-complexity tool with an output schema, the description covers the essential invocation logic and safety gating. It could add a caution about permanent removal, but the dry-run and confirmation mechanism is enough for a correct call.

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 is essentially an empty catch-all object (0% coverage), so the description is the only source of parameter meaning. It explains the two key parameters—execute and confirm—and their role in switching from dry-run to actual deletion. This fully compensates for the schema's lack of detail.

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 clearly states the tool's core function: dry-run listing of stopped containers for removal, with real deletion gated by flags. This distinct action differentiates it from sibling tools like docker_containers or docker_stats, which only observe container state.

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?

It explicitly says when to perform a dry-run versus a real delete (by setting execute=true, confirm=true), which is the main usage decision. It does not reference alternative tools for similar tasks, but the guidance is clear and actionable.

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