blender_ai_refine

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

With no annotations, the description carries the disclosure burden and does a good job: it reveals the render-evaluate-return sequence and implies the tool does not itself apply suggestions since it says to apply them between calls. It could still be clearer about side effects and external dependencies, but the core behavior is transparent.

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 with no filler, and the most important scoping ('one iteration') is front-loaded. The loop instruction earns its place by explaining the intended calling pattern.

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 description covers the iteration workflow but omits return-shape details (no output schema) and does not clarify how it relates to blender_refine_iteration or the session-management tools. An agent may still be unsure which refinement tool to select.

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%, so the parameters are already well documented. The description adds no parameter-specific meaning beyond the loop/convergence context already reflected in max_iterations and quality_threshold.

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 uses a concrete verb and resources: 'render object, evaluate with vision model, return scores and suggestions,' so an agent can infer the operation. It does not explicitly distinguish this from nearly identical siblings like blender_refine_iteration or blender_ai_evaluate, so it falls short of a 5.

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 gives explicit usage context: 'Call repeatedly in a loop, applying suggestions between calls, until converged.' This tells the agent the intended workflow, but it does not say when to prefer this tool over the session-based or evaluation siblings.

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