prune_system

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

With no annotations, the description must disclose safety and behavioral traits. It only says 'show or perform' without explaining that pruning is destructive and irreversible, nor that dry_run defaults to true. This is a significant transparency gap for a potentially data-deleting operation.

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, short sentence without wasted words. However, the brevity creates ambiguity (e.g., 'summaries'), which could have been clarified in the same length. Still, it is appropriately concise.

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 has no output schema or annotations, and the description doesn't explain the return format, the safety mechanism (dry_run), or the conditions under which actual deletion occurs. For a pruning tool that can remove data, this is incomplete guidance.

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 schema fully documents both parameters (format and dry_run) with descriptions and defaults. The description adds no additional parameter meaning beyond what the schema already provides, so the baseline of 3 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 clearly identifies the tool as dealing with Docker system prune operations and indicates two modes ('show or perform'). It distinguishes from sibling tools like disk_usage or list_containers by focusing on pruning, though 'summaries' is a bit vague.

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?

There is no guidance on when to use this tool versus alternatives, nor any conditions under which pruning is appropriate. No exclusions or alternative tools are mentioned, so the agent receives no contextual direction.

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