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

Annotations already declare non-read-only, open-world, non-idempotent behavior, so the bar is lower. The description still adds real value by disclosing the credit cost ('Uses one House AI design credit'), which the agent needs for cost-aware decisions; it does not say whether the source photo is preserved or output is returned as a new asset.

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?

A single front-loaded sentence with the core action, followed by concrete examples and the cost note. No wasted words.

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 generative mutation tool with no output schema and fully documented params, the definition covers purpose, examples, and the credit cost. It omits what the result looks like and whether a failed generation consumes a credit – a modest gap.

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 schema already documents photo, photo_url, floor_style, and photo_upload_id. The description's style examples overlap with the floor_style schema example ('white oak herringbone'), leaving baseline 3 appropriate.

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 ('Replace the floor in a room photo with new flooring') and frames the goal (preview a renovation). It does not name or contrast with close siblings like paint_walls or redesign_room, so it falls short of full sibling differentiation.

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 phrase 'to preview a renovation' implies the use case, and flooring-style examples suggest when the tool fits, but there is no explicit when-not guidance or pointer to alternatives such as redesign_room for broader changes. Usage is inferable rather than stated.

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