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

The annotations already declare readOnlyHint and non-destructive, so the safety profile is covered. The description adds real context beyond that: it returns step-by-step guidance with screens, buttons, and fields, and performs no action itself. That is exactly the behavior an agent needs to know, although it never says what the steps contain or how long they are.

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 operative information is front-loaded, but the final sentence, 'Brandfolder's official API: Yes.', adds no meaning for an agent and dilutes the otherwise tight call guidance.

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 parameters and no output schema, the description still explains what the return value, namely step-by-step instructions, contains. For a simple wrapper tool, that is nearly complete, though it doesn't say whether account context is assumed or what triggers a failure.

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?

The tool takes zero parameters, so 4 is the baseline. The description has nothing extra to explain about parameters.

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 specifically that it produces a step-by-step how-to for creating a collection in Brandfolder (screens, buttons, fields) and explicitly says it opens nothing by itself. That distinguishes it from the cotlet_browser_* tools it points to. It never contrasts with sibling write-ish tools like brandfolder_add_asset_to_collection beyond the mention that it acts in the user's own account.

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 definition gives a clear usage sequence: call this for the steps, then perform the action with the cotlet_browser_* tools in the user's Brandfolder Cloud Browser. It doesn't say when to pick cotlet_app_guide instead, so there is a small gap.

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