blender_turntable

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 that solid/wireframe skip the GPU guard, that the scene is restored after rendering, and that execution is refused while ComfyUI runs a job or VRAM is low unless ignore_gpu_guard is set. Remaining gaps are engine/timeout behavior and whether a partial failure still writes images.

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?

Front-loads the core action and orientation convention, then uses a compact mode enumeration and two short behavioral sentences. The mode block is dense but each clause carries information; no filler sentences.

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 an 8-parameter tool with 0% schema coverage and no output schema, the description covers the two most consequential parameters (mode, ignore_gpu_guard) and the light value, but leaves views, elevation, size, engine, and timeout undefined in both schema and prose. An agent can call it at defaults, but cannot confidently tune resolution, view count, or camera pitch.

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 0%, so the description must compensate. It explains mode's five values and the light parameter's role as a temporary offset key light, but says nothing about size, views, engine, timeout, or elevation despite them materially affecting output. Partial compensation only, so a 3 rather than higher.

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 precise verb and resource ('Render evenly spaced turntable views of all visible meshes') and adds a concrete semantic anchor ('View 0 = front (-Y)') plus a return statement ('returns the images'). This clearly distinguishes it from blender_render, blender_render_scene, and blender_screenshot, which lack the orbit/turntable framing.

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?

Gives actionable selection guidance for the mode parameter (material/solid/wireframe for speed, normal/mask for data) and states the conditions under which it refuses plus the escape hatch (ignore_gpu_guard=True). It stops short of explicitly naming a sibling alternative, e.g. when to prefer blender_render_scene or blender_screenshot over this, so it is clear but not fully routing.

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