metahuman_import

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says it 'registers' a package and 'scans' its asset tree, but does not disclose side effects such as whether registration modifies project files, overwrites existing registrations, requires Unreal to be running, or what the scan produces. For a mutation-like registration action with zero annotation coverage, this is a significant gap.

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 compact—two sentences plus an example and a KB pointer—with the core purpose front-loaded. Every element earns its place; the example is useful for grounding the call signature, though the KB link adds some external dependency.

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?

Despite having an output schema and being a complex 6-parameter import tool with a scanning behavior, the description does not explain prerequisites (does the package need to exist? is Unreal required?), the meaning of the four undocumented parameters, or what the returned scan report contains. The KB reference helps but the description alone is too thin to fully guide correct invocation.

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 for parameter meaning. The example hints at character_name and metahuman_root, but four of six parameters (create_manifest, body_skeletal_mesh, expected_blueprint, face_skeletal_mesh) are never mentioned. The description adds marginal value over the schema for only two of the parameters and does not explain their purpose or defaults.

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 states a specific verb+resource ('Register an assembled MetaHuman package and scan its imported asset tree'). This is clear about what the tool does and is distinct enough from the metahuman_* sibling family, though it doesn't explicitly name the sibling it differs from (e.g., metahuman_inspect_package).

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?

A concrete example is provided (character_name='Ada', metahuman_root=...), which helps an agent infer how to invoke it, and a KB reference points to pipeline context. However, there is no explicit guidance on when to use this tool versus alternatives like metahuman_inspect_package, metahuman_link_to_skeleton, or metahuman_assign_dna, nor any exclusions or prerequisites stated.

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