buildx_du

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context without contradicting annotations. It discloses truncation behavior, partial-record dropping, error raising (RuntimeError), and the workaround for exhaustive output. This goes well beyond the structured annotations.

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 appropriately sized for a tool with notable caveats. It front-loads the core purpose, then provides practical warnings and finally structured arg/return notes. Every sentence adds value, and the layout is easy to scan.

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 one optional parameter, no output schema, and moderate complexity, the description covers the essential aspects: what it reports, how it might fail, how to get complete results, error behavior, parameter semantics, and return format. No significant gaps remain.

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 input schema provides no description for the builder parameter, so the description's 'args: builder - Override the active builder' is essential and adds meaning. It also documents the return type as 'list - One dict per cache record'. With only one parameter, this is sufficient compensation for the 0% schema coverage.

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 specific action and resource: 'Report BuildKit cache disk usage as a list of records.' It clearly differentiates from siblings by contrasting with system_df ('covers daemon-side disk, not builder cache') and buildx_prune ('Reclaim the cache').

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 clear usage context, explicitly noting when the tool may be insufficient (large caches exceeding MAX_CLI_OUTPUT_BYTES) and suggesting a host-side command for exhaustive reporting. It also directs to buildx_prune for reclaiming cache and clarifies that system_df is not a substitute. However, it does not explicitly enumerate alternative tools for the same job.

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