bake_texture

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

With no annotations, the description carries the burden and does well: it discloses that Cycles is used, that the render engine is restored afterwards, that a file is written to disk, and that samples/ray settings trade quality for time. It omits whether the material node tree must contain an image texture target (a common Blender bake failure) and says nothing about bake duration or failure modes.

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, then a compact Args block where each line adds a distinct fact (range, format, or when to adjust). No filler sentences, and the frequent-bake caveats ('raise it if the bake has holes', 'clean at 1 to 16') are the kind of detail that earns its space.

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, file-writing operation with no annotations, the description covers prerequisites, side effects, parameter ranges, per-enum guidance and the return shape. An output schema exists, but the Returns note is a one-line complement rather than a substitute, and nothing an agent needs to call it correctly appears absent.

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 0%, so the description must compensate, and it documents all 11 parameters: enum meanings for bake_type, format guidance for filepath, numeric ranges for resolution/cage_extrusion/max_ray_distance/margin/samples, and the semantic role of source_object, diffuse_color_only and normal_space. This adds substantial meaning beyond bare typed properties.

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 ('Bake a texture map from an object's materials ... into an image') and covers both modes: self-bake and high-poly-to-low-poly transfer. An agent can distinguish this from siblings like render_image, create_raster_texture, or smart_uv_project without opening any schema.

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?

Prerequisites are stated explicitly: the object needs UVs (naming smart_uv_project) and a material, and the output directory must already exist. It also gives selection guidance inside parameters (game engines want DIFFUSE + diffuse_color_only, .exr/.png for normal maps). It stops short of saying when to prefer this over render_image or procedural texture alternatives.

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