build_part

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

With no annotations, the description carries the full burden and does so well: it discloses sandboxing, timeout behavior, cache location and reuse conditions, fresh rebuild semantics, that no other files are written, per-piece timing hints, and error reporting with tracebacks. This is unusually rich behavioral context for a build tool.

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 dense and front-loaded with the core action and reporting behavior. It is somewhat run-on and packs many details into long clauses, but nearly every clause provides useful operational context rather than 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 complex build tool with an output schema, the description covers execution environment, cache behavior, output summary, timing hints, errors, and follow-up review steps. The main gap is that it never explains the required `name` argument, which is important context for invoking the tool correctly.

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 0%, so the description must compensate. It explains `variant` (key from VARIANTS, 'standard' = ''), `parts` (comma-separated piece names from build(), lazy pieces skipped), and `fresh` (rebuild and replace cache), but the required `name` parameter is never described.

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 states a specific verb and resource: run the part script and report per-variant/part geometry, validity, errors, and timing. It also distinguishes itself from render_preview, section, check, and export by explaining cache reuse, though it does not clearly identify the required `name` argument's role in that purpose.

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 gives clear usage context: `parts` limits which pieces are built, lazy pieces are skipped, cached pieces are reused later, and `fresh=True` rebuilds and replaces cache. It also mentions `before_printing` review steps, but does not explicitly compare when to call this versus siblings like `new_part`, `read_part`, or `diagnose_failure`.

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