mesh_set_backfaces

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

Annotations already declare it non-destructive/non-read-only, and the description adds genuinely new behavioral context: the effect is per-object and non-persistent ('lost on re-import'). That transient-state caveat is exactly the kind of information annotations cannot convey.

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?

One compact sentence plus a short trailing caveat, with the action and scope front-loaded. Nothing is padded, though the parenthetical and shader analogy are slightly redundant with each other.

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 an output schema and annotations present, the description covers the essentials of a small two-parameter tool. It still omits the meaning of toggling show off and the accepted ref forms, which an agent must guess before calling correctly.

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 burden falls on the description; it partially compensates by explaining that refs absent means 'all meshes' and provided means 'the given ones'. However, the accepted reference forms (int index vs. string name) and the semantics of show=false (restore culling) are left undocumented.

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 ('Show back faces (cull back faces off) on all meshes or the given ones') with a concrete scope of all vs. selected objects. No sibling in the list deals with backface culling, so there is little risk of confusion, though it does not explicitly contrast with e.g. object_set_visible.

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?

'on all meshes or the given ones' implies the targeting rule (omit refs = whole scene), and 'lost on re-import' hints that this is a viewport/display-only setting rather than a saved material change. There is no explicit statement of when an agent should choose this over material-related tools or whether it applies to selection.

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