create_enum

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

Annotations only declare readOnly/not-idempotent/not-destructive. The description goes well beyond: it warns the call errors when the asset exists, and explains the display-name vs internal NewEnumeratorN split, including the silent first-space truncation that lands writers on index 0. That is exactly the kind of non-obvious failure mode annotations cannot carry.

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, and the dense middle sentence about the display/internal split earns its length because it prevents a silent data bug. It is slightly long and the 'Returns' line sits after the long warning, but nothing is padding.

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?

With no output schema, the description supplies the return shape ({ name, path, entry_count }), the failure condition, the naming convention risk, and the follow-up tools. An agent has everything needed to call this correctly and to predict what happens to downstream DataTable references.

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 baseline is 3, but the description adds real meaning: 'entries' takes DISPLAY names (not internal ones) and must be ordered, and the internal NewEnumeratorN names are what DataTable writers must actually use. It does not add detail on `path`/`asset_path` beyond what the schema already states.

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 ('Create a Blueprint enum asset') plus the input shape ('from an ordered list of enumerator DISPLAY names'). It explicitly routes editing work to the sibling tools add_enum_entry / rename_enum_entry / reorder_enum_entry, so an agent can separate create from edit without opening any 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?

Gives clear when-to-use context (creating an enum asset) and names the alternatives for subsequent mutation ('add_enum_entry / rename_enum_entry / reorder_enum_entry edit it afterwards'). It also flags the non-idempotent failure mode. It stops short of explicit 'do not use this to modify an existing enum' phrasing, hence not a 5.

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