buildx_prune

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

Annotations already mark destructiveHint=true and idempotentHint=true. The description adds that --force is always passed, explaining why (no interactive prompt). This provides useful behavioral context beyond the annotations, such as the subprocess timeout and return format.

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?

Extremely concise: one-line purpose, a critical warning, a structured parameter list with clear labels, and return type. No wasted words, and important information is front-loaded.

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?

Covers purpose, parameters, return format, and destructive behavior. Missing prerequisites like need for an active builder, but given the complexity and no output schema, it is largely complete. The pairing suggestion enhances completeness.

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?

Despite 0% schema coverage, the description explains all 7 parameters with examples (e.g., filters with JSON format) and defaults (e.g., timeout_seconds). This adds significant meaning, though a bit more detail on builder would help.

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?

Clearly states the tool removes BuildKit cache entries, specifying the resource and action. The destructive nature and force flag are highlighted, distinguishing it from other prune tools like container_prune or image_prune.

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?

Recommends pairing with buildx_du first to inventory cache, which is good guidance. However, it does not explicitly differentiate from other prune siblings or state when not to use, though the specificity to BuildKit cache implies its scope.

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