save_dataset

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

No annotations are supplied, so the description carries the full burden. It does add real context: writes are confined to HIDIM_ROOTS, npz preserves dims+coords and is reloadable, nc requires xarray. It omits the most consequential write-side behavior — whether an existing file at the target is overwritten, whether directories are created, and what errors occur on failure.

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?

Front-loaded with the action and the root constraint, then two compact format lists. Nearly every token earns its place; the only friction is telegraphic repetition of "mat" across both the table and tensor lists and a missing space in "dims+coords".

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?

An output schema exists, so return values need not be described, and the format support matrix is well covered. For a disk-writing tool with no annotations, however, the missing overwrite semantics, path resolution rules, and the meaning of `name` leave genuine gaps an agent needs before calling it safely.

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 all three parameters rely on the description. The format options are effectively enumerating the values for `format` (which the schema types only as a bare string), which is genuine added value, but `name` and `path` are never explained — notably whether path is relative to HIDIM_ROOTS or absolute, and what name identifies.

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 concrete verb+resource ("Write a dataset to disk") plus the enclosing constraint ("under HIDIM_ROOTS"), which cleanly separates it from siblings such as load_dataset, list_datasets, and drop_dataset. It never names a sibling explicitly, but the write-vs-read contrast is unambiguous.

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?

Usage is only implied: the tool is the persistence step and the format lists tell you which format suits tables vs tensors. There is no explicit when-to-use/when-not guidance (e.g., vs save-style alternatives, or when to prefer npz over nc for reloadable tensors beyond the parenthetical).

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