geometry_nodes.create_group

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

Annotations are all false (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so they signal mutation but provide no detail. The description adds only 'Risk: standard; maturity: L3', which is generic boilerplate. It does not explain what the command changes in the scene, whether an existing group is replaced, whether it requires an active geometry nodes modifier, or how the operation participates in transactions.

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?

The description is short, but it wastes its two sentences on restating the command name and generic policy boilerplate. It front-loads no actionable information. With 8 parameters, including an undocumented 'inputs' array, the description is under-specified rather than efficiently concise.

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?

Given the tool has 8 parameters, 38% schema coverage, no enums, no nested-object documentation, and an output schema exists, the description still leaves the core semantics unexplained. An agent cannot know what 'create group' means in this harness, what the required parameters should contain, or what the success/error response looks like. The output schema exists, but the description doesn't tie the tool's behavior to it. It is inadequate for a command with this complexity.

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 38% and only the underscore-prefixed harness control parameters (_requestId, _authorization, _transactionId, _expectedSceneRevision) have descriptions in the schema. The four main parameters (groupName, modifierName, object, inputs) are entirely undocumented in both the schema and the description. The description does not clarify whether groupName is the node group's name or the modifier's group instance name, nor what the 'inputs' array should contain. The description adds zero semantic value over the bare parameter names.

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?

The description is essentially just the command name 'PartMe Blender Harness command `geometry_nodes.create_group`' – it restates the tool name without stating what 'create_group' actually does (creates a Geometry Nodes modifier group? A node group within the modifier? Attaches it to an object?). It doesn't specify the verb action beyond the name itself, nor does it distinguish from siblings like blender_geometry_nodes_add_node or blender_modifier_add. The mention of 'Risk: standard; maturity: L3' is metadata, not purpose.

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?

No guidance on when to use this tool versus alternatives. The sibling list includes many geometry-nodes and modifier tools (blender_geometry_nodes_add_node, blender_geometry_nodes_connect, blender_modifier_add), but the description doesn't explain how create_group relates to them. 'Per-request argument checks and session policy still apply' is a generic harness policy statement, not usage guidance.

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