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

With no annotations, the description carries the full burden and does well: it discloses the 30-90 second render latency, that the result may not be ready in time, and that a returned id must be polled via get_visualization. It does not mention auth requirements, cost, or rate limits, which are the remaining behavioral gaps.

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?

Two sentences, front-loaded with the outcome, then inputs, then the async fallback. No filler and every clause carries operational 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?

There is no output schema, and the description correctly compensates by stating what comes back (an image plus a price estimate) and how to retrieve it later. It stops short of covering failure modes or the cost/auth context an agent might need.

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; the description adds value by naming accepted image formats (JPEG/PNG/WebP) and tying stone_slug back to search_stones. sqft is left entirely to the schema, but it is well documented there.

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+resource ('Render a slab ... onto a photo of the user's own kitchen or bath') plus the two outputs it produces (image and price estimate). It also implicitly separates itself from the sibling get_visualization by describing this as the initiating call.

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?

Tells the agent the prerequisites (a public room image URL and a stone slug sourced from search_stones) and routes to the alternative when the render is not ready ('call get_visualization with the returned id'). No explicit when-not-to-use case is given, but the async handoff rule is clear.

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