dataset_create

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

The description asserts 'Non-destructive (creates new storage)' while annotations declare destructiveHint=true, a direct contradiction that could mislead an agent about whether user confirmation is warranted. It also omits other behaviors an agent needs, such as what happens when the dataset already exists (annotations say non-idempotent) or what the response contains.

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?

Well front-loaded: the write marker and one-line purpose come first, then the preview hint, then parameters. The 'No undo descriptor' sentence is slightly awkward and the Args block partially echoes the schema, but each line adds usable information.

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 4-parameter mutation tool with no output schema, the description covers parameters and preview behavior but leaves key operational gaps: no return shape, no statement of what happens on a name collision (non-idempotent per annotations), and no permission/target prerequisites beyond 'from config'. Adequate but not complete.

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 0%, so the description must carry the burden, and it does document all four parameters with meaning: 'name' is a full dataset path with a concrete example ('tank/projects'), 'pool' is optional context/labelling, 'dry_run' previews, and 'target' is a config target name. The name/pool distinction in particular resolves genuine ambiguity the bare schema leaves open.

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 ('[WRITE] Create a ZFS dataset'), which is unambiguous and immediately distinguishes it from dataset_list, dataset_get, and snapshot_create siblings. An agent can select this tool without opening the schema.

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 a condition for dry_run ('Pass dry_run=True to preview') and states that deletion is out of scope, which implicitly tells the agent this tool never removes data. However, it never names an alternative or states the prerequisite/preconditions for creating a dataset (e.g., pool must exist, target must be configured), leaving usage largely implied.

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