golden_import

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

No annotations are provided, so the description carries the full disclosure burden and meets it: it states the side effects ('imported, snapshotted where it stands and recorded as a golden image'), lifecycle ('durable that only the user can remove'), and non-behaviors ('no recipe and no download', 'nothing is seeded', no cloud-init to wait for). This is far richer than what the tool name alone would reveal.

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?

Five sentences, each with a distinct payload: core purpose, sibling contrast, side effects, credential workflow, and durability caution. It is dense and not front-loaded beyond the first sentence, but the length is earned given 5 parameters, multiple related siblings, and significant side effects to disclose.

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?

Output schema exists, so return values need no explanation. The description covers purpose, alternatives, side effects, durability, and the credential-discovery workflow. Minor gaps remain—idempotency on re-import and expected duration for a VM import—but nothing that would block a correct invocation.

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 description coverage is 100%, so the baseline is 3. The description adds genuine value on top by explicitly declaring credentials (key, user, password) optional and prescribing the fallback workflow when they are unknown, which the schema only hints at with 'if it is known'/'if there is one.'

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?

Opens with a specific verb+resource+outcome: 'Register an .ova or .ovf appliance file already on this machine as a golden image.' It explicitly differentiates from the closest sibling ('Unlike golden_get there is no recipe and no download') and cross-references golden_adopt, so an agent can tell this tool apart from related golden-* tools 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?

Names golden_get as the alternative and states the differentiator (recipe/download vs. local import). It also prescribes a full decision path: import without credentials, discover login via env_fork/env_screenshot/env_type, record with golden_adopt, and warns 'do it when the task asks for it' for a durable resource. Nothing is left to inference.

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