create_snapshot

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

No annotations are provided, so the description carries full burden. It does not disclose any behavioral traits such as permissions required, effects on the dataset (e.g., does it lock the dataset?), behavior if snapshot already exists, or what the output looks like. The description is silent on all behavioral aspects, offering no actionable info beyond 'creates a snapshot.'

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 extremely concise—one sentence of five words. While brevity is valued, it sacrifices necessary detail for a tool with three parameters and no annotations. Every word is used, but the single sentence lacks structure or elaboration. A score of 3 represents a fair balance but indicates room for improvement.

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?

Given the tool has three parameters (two required), no annotation, and 0% schema description coverage, the description is inadequate. It fails to explain the purpose of parameters, output schema contents, or side effects. The presence of an output schema (without description) does not relieve the need for behavioral context. The description is too sparse to be considered 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%, and the description adds no explanations for the three parameters (dataset, name, recursive). The agent must infer meaning from parameter names alone. For example, 'name' could be a snapshot name or a tag, and 'recursive' could apply to child datasets; no clarification is given.

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 'Create a manual ZFS snapshot,' clearly identifying the verb (create) and resource (snapshot). It distinguishes from sibling tools like clone_snapshot, delete_snapshot, and list_snapshots, but does not explicitly differentiate from create_dataset or other creation tools. The word 'manual' hints at one-time operation vs. scheduled tasks.

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?

No guidance on when to use this tool versus alternatives like clone_snapshot or rollback_snapshot. No prerequisites, context, or exclusions provided. The agent receives no help in deciding if this is the right tool for a given request.

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