golden_get

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

With zero annotations, the description carries the full burden and delivers: it discloses that the operation is slow and bandwidth-heavy, downloads ~500 MB, boots once for cloud-init, takes minutes (up to an hour for Windows), and fails if the golden already exists. This is exceptional behavioral disclosure covering performance, side effects, process steps, and failure modes.

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 core action is front-loaded in the first sentence, and every subsequent sentence earns its place: performance profile, process steps, the `from` variant, and the failure caveat. It is long (~120 words), but the tool genuinely has two modes and heavy operational consequences, so the density is justified with no wasted phrasing.

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, long-running, resource-heavy build operation with no annotations and an output schema present, the description covers all essential ground: purpose, step-by-step behavior, expected duration, failure condition, and how to source valid inputs. The output schema handles return values, so nothing critical is missing.

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 100%, so the schema already documents all three parameters, giving a baseline of 3. The description adds genuine value on top: pointing to recipe_list as the source for valid image values and explaining that a `from`-recipe changes the build semantics. cpus and memory_mb receive nothing extra, but they need nothing.

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?

States a specific verb and resource — 'Build a golden image from a recipe' — and immediately explains the purpose ('so environments can be forked from it'). The workflow detail (importing, booting for cloud-init, snapshotting) clearly separates it from related siblings like golden_import and golden_adopt, so an agent can distinguish them without opening their schemas.

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?

Gives explicit direction to consult recipe_list for valid image names and warns that rebuilding an existing golden is a human decision, an implicit when-not-to-use. It also distinguishes the two recipe modes (base vs `from`). However, it never explicitly contrasts with golden_import or golden_adopt, which are the closest alternative tools.

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