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

With no annotations, the description fully discloses behavior: it returns a URL, opening it starts the studio, generates from the user's sentence, shows a preview, and is free. It clearly states it does not generate anything itself, preventing misuse, and no contradictions exist.

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?

Four sentences, each serving a distinct purpose: context, explicit limitation, workflow, and scope/responsibility. Front-loaded with the key action ('returns a URL') and no redundant information.

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?

The tool is simple, and the description covers purpose, workflow, and what the agent should do with the URL. It also clarifies cost and human responsibilities, making it complete even without an output schema.

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. The description only indirectly references the prompt via 'their sentence' and adds no new meaning to the product parameter beyond the schema's enum. It does not explain parameter values or constraints.

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 clearly states the tool returns a URL rather than generating a design, using specific verb 'returns a URL' and contrast 'does NOT generate anything.' It distinguishes from siblings (get_design, search_designs) by emphasizing 'NEW design' and 'invent a motif that does not exist yet.'

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?

It explicitly says 'Hand that URL to the human' and 'Size choice, legal notices and payment stay with the person,' providing direct when-to-use and when-not-to-use guidance. It also contrasts with sibling tools by noting it does not generate, making intended usage clear.

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