add_essentials_modifier

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

With no annotations, the description carries the full burden and does substantial work: it discloses that a complete node group is instantiated, that Object/Collection inputs resolve by existing name, that menu inputs take the Blender-displayed option label, and what the return payload contains. It omits whether the essentials asset must be available/version-gated and what happens on an invalid input name, which are meaningful gaps for a mutation tool with zero annotation coverage.

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?

Purpose and the sibling distinction are front-loaded in the first two sentences, and the per-modifier input list is directly actionable rather than filler. The enumeration is long, but each entry maps to a real enum branch an agent must choose between, so it 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?

An output schema exists, so the description needn't define return values, yet it still summarizes them. All three parameters are documented despite 0% schema coverage. The remaining gap is operational: nothing says whether the essentials asset library must be bundled or which Blender versions expose these, which matters for a 3-param tool with no annotations.

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 entirely, and it does: it enumerates every enum value with the inputs each one exposes, gives a concrete settings example ({"Object": "Rock", "Amount": 200}), and explains the two non-obvious value conventions (names for Object/Collection, display labels for menus). This is materially more than the bare schema allows.

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 (add Blender's ready-made node modifiers) and immediately distinguishes itself from the low-level sibling path by noting these are full node setups that would take dozens of add_geometry_node calls. An agent can tell this apart from add_modifier, create_geometry_nodes, and add_geometry_node 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?

Explicitly names the follow-up alternative and its condition: 'Change inputs later with set_geometry_node_input.' It also frames the tool's niche relative to add_geometry_node. It stops short of stating when to prefer the classic add_modifier or create_geometry_nodes over this, so the boundary with those siblings is only implied.

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