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

Annotations already declare readOnly=false, destructive=false, openWorld=true and non-idempotent, so the safety profile is covered. The description adds a genuinely non-structured behavioral fact: each invocation "Uses one House AI design credit," which is exactly the kind of cost signal an agent should weigh before calling. It stops short of covering async/latency or what a failed or low-credit run yields.

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 core definition, followed by the cost note. No waste, though "for a new home, a rental or a listing" is the softest part and could be tightened without loss.

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 output schema and a nested photo object, the description plus the rich schema descriptions together are sufficient to call it correctly. The remaining gap is what comes back — a staged image, presumably listed under list_my_designs — and whether credits are consumed on failure, neither of which is stated.

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 description coverage is 100% and the schema itself distinguishes the three mutually exclusive photo inputs (attached photo, photo_url, photo_upload_id) with clear per-field notes. The description only echoes "from a photo in a chosen style" and adds nothing about which photo channel to prefer, so the 100%-coverage baseline of 3 applies.

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?

"Virtual staging: furnish and decorate an empty or bare room from a photo in a chosen style" gives a specific verb pair, the resource (a room photo) and the required input dimension (style). The word "empty" implicitly separates it from a redesign of an already-furnished room, though no sibling is named.

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?

"for a new home, a rental or a listing" gives audience context and "empty or bare room" scopes the input, which is a usable condition for selection. But there is no explicit exclusion or routing — it never says to use redesign_room when the room already has furniture, or empty_room when the goal is removal, so the agent must infer the boundary.

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