rig_creature

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

With no annotations, the description carries the full burden and does disclose meaningful traits: loops close exactly, one-shots end on the setup pose, the artist's setup never moves, and the result reports bones/slots/constraints plus qa.budget(mobile_character). It omits what project/file state is mutated, whether seed makes runs deterministic/reproducible, and any idempotency guarantees.

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-loads the core action and layer convention, then organizes per-kind behavior into an indented, scannable list. It is long and duplicates detail that kind="" would return at runtime, but nearly every line carries decision-relevant physics/gait/event information rather than filler.

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 a complex 8-kind generator with no output schema, the description is largely self-sufficient: it details clips, physics, events, loop/one-shot end states, and what the result reports. Gaps remain around prerequisites, which assets/skeleton it writes to, and the meaning of seed/project/exaggerate.

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% across 6 params, so the description must compensate and only partly does: it explains kind (with a '' enumeration shortcut), clips (per-kind listings) and some options keys (options.law="area"). It says nothing about seed, project, or exaggerate, leaving a third of the parameters undocumented for a tool with no schema-level help.

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+resource+scope: 'Rig a non-humanoid creature from its layers and build its clip set', immediately distinguishing it from the humanoid rig_biped and naming the sibling rigs it composes (rig_quadruped, rig_serpent, rig_flier). An agent can identify exactly what this tool produces without opening the 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?

Gives clear operating context: kind="" enumerates every kind with its layer convention, clips and options, which is a concrete entry point, and the 'non-humanoid creature' framing implicitly separates it from rig_biped. However it never explicitly says when to call it instead of using the composed rigs (rig_quadruped/rig_serpent/rig_flier) directly, nor states prerequisites such as an imported PSD.

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