buildx_du

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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses critical behavioral traits: potential truncation of stdout with loss of the final partial record, the parsing approach from JSON format, and that RuntimeError is raised on CLI failure. This gives the agent a realistic model of the tool's limitations.

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 compact yet information-dense. The purpose is front-loaded in the first sentence, followed by essential caveats, error behavior, and parameter/return documentation. Every sentence serves a purpose with no repetition or filler.

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 simple tool with one optional parameter and no output schema, the description covers all needed context: return type (list of dicts), error handling, truncation risk, and the relationship to sibling tools. It even clarifies the distinction between daemon disk (system_df) and builder cache (buildx_du), making the tool's role fully understandable.

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 0% schema description coverage, the description compensates by explaining the only parameter: 'builder - Override the active builder.' This adds meaning beyond the raw type/default. It could be more detailed about default behavior (e.g., uses active builder when null), but the phrase 'Override the active builder' is sufficiently clear for an optional parameter.

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 opens with a clear, specific statement: 'Report BuildKit cache disk usage as a list of records.' It distinguishes itself from siblings by explicitly contrasting with buildx_prune (reclaim) and system_df (daemon-side disk), making its unique scope obvious.

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 provides explicit when-to-use guidance, including a caution about truncation for large caches and advice to run the CLI directly for exhaustive results. It also directs users to buildx_prune for reclamation and clarifies that system_df does not cover builder cache, preventing incorrect tool selection.

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