buildx_bake

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

Over and above the annotations, it discloses a key behavioral twist: non-zero CLI exits do NOT raise, while a missing plugin or timeout DOES raise, and the agent should inspect `returncode`/`stderr`. It also adds the real-world nuance that `cwd` is copied to the target host when no local plugin is present. These are non-obvious behaviors that materially affect how an agent interprets results.

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 tightly organized: purpose, usage decision, exception/return behavior, parameter list, and return structure. Each line earns its place; there is no filler or repetition of what the schema already shows without added value.

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 10-parameter tool with no output schema, this description is thorough: it documents the args array, the return dict shape, default values, and atypical exit behavior. It gives an agent everything needed to invoke it correctly and interpret results confidently.

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 carries the full burden for all 10 parameters. It covers each parameter with meaningful prose: `targets` default, `files` manual repeatability, `set_overrides` with an inline example, `cwd` copy behavior, and `timeout_seconds` default. This is excellent compensation for the sparse schema.

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 verb and resource: 'Build multiple targets defined in a bake file (HCL, JSON, or compose).' It also explicitly differentiates from the single-target sibling (`buildx_build`), so an agent can immediately tell which tool is for which job.

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?

It explicitly states when to use the tool ('Use it for multi-target builds declared in docker-bake.hcl/compose files') and when not to, directing single Dockerfile targets to `buildx_build`. This is clear, actionable, and leaves little room for misinterpretation.

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