clip_set

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

With no annotations the description carries the full burden and delivers substantial behavior: loops close exactly, one-shots end on the setup pose, the setup is preserved, missing-bone clips are skipped and reported, and a full event set (sfx_step, sfx_jump, attack_hit, etc.) is emitted. It stops short of disclosing write/overwrite semantics (does it replace existing clips?) or permissions, which are the main residual gaps.

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 core concept is front-loaded in the first sentence, but the body is a dense wall of physics exposition (inverted pendulum, spring-mass, gravity-parabola flight, wind v^2) that informs what clips look like more than how to invoke the tool. The clip/event inventories earn their place; the physics prose is verbose relative to invocation needs.

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 9-parameter tool with no annotations and no output schema, the description covers clip identity, events, physics, and rig/bone-mapping behavior well. It is still incomplete on the required project parameter, the facing and attack_hand selectors, the wind flag, and overwrite semantics, leaving an agent to guess at invocation details.

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 coverage is 0%, so the description must compensate, and it does for several parameters: bone_map (with a concrete rename example), intensity (0.5 subtle … 1 standard … 1.6 cartoon), durations ({clip: seconds}), and blow_from (front|back). It leaves project (the only required param), clips, facing, attack_hand, and wind unexplained, so coverage is partial rather than complete.

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 opening line frames the tool as the standard animation-clip contract, and the enumerated clip list (idle, walk, run, jump, land, hit, attack, win, lose, talk) makes the resource concrete and distinguishes it from narrower siblings like gait, face_clip, and lipsync. The action verb is implied rather than stated (it never says 'creates/generates clips'), so an agent infers the operation from context.

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?

It gives an applicability condition ('works on any rig that has the bones a clip needs') and states that clips with missing bones are skipped, which is useful context. However, it never says when to reach for clip_set versus alternatives such as gait, add_keys, face_clip, or lipsync, and no prerequisites or sequencing are given.

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