System prune

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

The description adds significant value beyond annotations by explicitly labeling the tool as '[CRITICAL RISK]', noting that 'This cannot be undone!', and detailing the exact resources removed. This aligns with destructiveHint=true and provides crucial behavioral context.

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 a single, well-structured sentence that front-loads the risk warning and concisely states the action and scope. There is no redundancy or wasted words.

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?

Given the destructive nature and no output schema, the description adequately covers the core functionality and risks. It could benefit from explaining what 'unused' means or impact on running containers, but the annotations (destructiveHint=true) partially compensate.

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?

With 100% schema description coverage, the baseline is 3. The description adds no new information beyond the schema; it mentions 'optionally volumes' which matches the volumes parameter description in 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 clearly states the verb ('Perform Docker system prune') and resource ('Docker system'), and specifies what it removes: containers, networks, images, and optionally volumes. It distinguishes itself from sibling prune tools like image_prune, network_prune, and volume_prune by being more comprehensive.

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 implies this tool is for general cleanup of unused Docker resources but does not explicitly provide guidance on when to use it versus other prune tools (e.g., image_prune, volume_prune). There is no 'when-not' or alternative suggestions, limiting its utility for tool selection.

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