system_prune

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

No annotations are provided, so the description must fully disclose behavioral traits. It mentions returning a summary but does not explain destructive nature, required permissions, confirmation prompts, or error conditions. The description is insufficient for safe agent invocation.

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 sentences front-load the purpose and output, with a second sentence providing a key usage tip. Every word earns its place; no fluff or redundancy.

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 simple input (one enum parameter) and no output schema, the description is mostly adequate. However, it lacks detail on the return format beyond 'summary of reclaimed space', and does not cover edge cases like no unused resources. The overall completeness is sufficient but not exemplary.

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?

Schema coverage is 100%, so baseline is 3. The description adds value by noting that scope 'all' prunes every category and aggregates reclaimed space, which goes beyond the schema enum definition.

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 prunes unused Docker resources by scope and returns a summary. The verb 'prune' and resource 'unused Docker resources' are specific. It distinguishes from sibling tools like container_action or image_action, which operate on individual resource types.

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 usage for cleanup but provides no explicit guidance on when to use this tool versus individual sibling prune commands. It does not mention exclusions or alternatives, leaving the agent to infer context.

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