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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely non-obvious context: an AI art-director rewrites the prompt before generation, and results render in an inline 3D viewer. It does not disclose latency or whether the call is asynchronous, and idempotentHint=false is left unqualified despite the schema offering a 24-hour idempotency key.

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?

Output format and input modes are front-loaded, then the refinement behavior, then the usage cue. The final sentence largely restates the second ('higher quality ... prompt refined for you first'), so one clause is redundant.

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, the description still tells the agent the artifact type (GLB) and that it renders inline, and it explains the text-mode refinement step. The notable gap is whether a job is queued and should be polled via check_job/get_job, which the sibling list makes a realistic concern.

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 explains prompt, image_url, and the idempotency key in detail. The description adds only the nuance that text mode produces a 'single-subject spec', which hints at prompt constraints the schema's 'single object to model' already covers. Baseline 3 is correct when the schema does the heavy lifting.

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 ('Generate a textured 3D mesh (GLB)') and both input modes (text prompt or reference image URL). It positions itself as the higher-quality option versus a plainer generator but never names the sibling (forge_free), so differentiation is implied rather than explicit.

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?

'Use this when you want a higher quality mesh from a rough prompt or reference image' gives a clear selection condition, and the mention of prompt refinement signals the cost/quality tradeoff. It stops short of naming the cheaper alternative or stating when not to use it.

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