render_review

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

Adds substantial context beyond the annotations: it runs on a cloud GPU, costs the same as one preview, enumerates the concrete checks performed (texture files, hidden objects, camera inside geometry, framing, exposure, light), returns fix code per problem, and returns the 4 views tiled in one image. The annotations only carry the generic openWorld/non-idempotent profile, so the description is doing real work here.

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-loaded with the core action and output, then usage triggers, then the sibling routing rule. Every sentence carries information, but the block is long and the multi-language example strings ('モデルを確認して') add bulk without adding much decision value for an English-speaking agent.

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 11-parameter, zero-required tool with no output schema, the description covers what matters: the return shape (pass/warning/fail, score, checks, fix code, tiled image), the input alternatives, cost, and the boundary of what the checks can judge. Nothing an agent needs to invoke it correctly is missing.

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, but the description adds meaning the schema does not: it frames scene_path/scene_script/scene_url/scene_id as four alternative ways to supply the same scene ('Give the scene as ...'), which the flat schema never states. It also notes environment affects lighting choice. Minor gap: it does not explain orbit_distance/orbit_elevation semantics.

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 (check/review) and resource (a 3D model or generated Blender scene), and specifies the exact method: a 4-view turntable under neutral studio light returning pass/warning/fail, a score, and the checks run. It explicitly distinguishes itself from the sibling render_preview by naming the camera/lights case that selects the other tool.

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 explicit when-to-use triggers ('after writing a bpy script, generating or converting a model ... before showing the result to the user or rendering a final'), the loop to follow ('apply the fixes and call it again'), an explicit limitation ('the checks cannot judge whether the shape matches the request'), and the alternative for camera-based shots (render_preview). Nothing is left to inference.

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