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

Annotations already declare this is a non-readonly, non-destructive, non-idempotent, closed-world mutation, so safety characteristics are covered externally. The description adds the meaningful constraint that folders live in the signed-in user's library and that nesting must be same-scope and same-project (also in the schema). It stays silent on duplicate-name behavior, error modes, and whether the new folder is returned with an id.

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?

Three sentences, front-loaded with the core action, then scope semantics, then optional parameters. No filler; the only slight waste is re-enumerating the scope mappings that the schema already lists, though here it is used to add the upload_style_reference link.

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 mutation tool with no output schema, the agent still does not know what comes back — whether a folder id is returned and needed downstream, which matters for the reference-scope workflow the description itself invokes. The description implies the returned id is what upload_style_reference consumes but does not state it. Everything the agent needs to make the call correctly is present; the post-call picture is not.

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 baseline is 3, but the description earns an extra point by explaining the practical meaning of the 'reference' scope — it is the folder that supplies folder_id to upload_style_reference. That cross-tool semantic is not conveyed by the schema's one-line enum descriptions. Parent/project parameters are only restated, not enriched beyond the schema.

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 gives a specific verb and resource ('Create a folder inside the signed-in user's library') and then decodes the three scope values into their product-surface equivalents, which is the actual ambiguity of this tool. It stops short of naming any sibling it should be chosen over, but there is no competing folder-creation tool in the sibling list, so an agent can still place it correctly.

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?

The description supplies context for choosing a scope ('reference' is where the folder_id for upload_style_reference comes from), which is genuine routing guidance to another tool. It does not say when not to use it, what to do if a similarly named folder already exists, or how choosing a project vs. no project affects later calls — guidance is implied rather than stated.

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