set_clip_kindA reaction plays once (rest → motion → rest). A state enters its pose, loops the held part for as long as it is playing, then exits (talk, think, sleep). Switching to state needs a clean held loop in the clip; free.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| clip | Yes | The clip's name or id | |
| kind | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the idempotentHint annotation, the description discloses meaningful playback semantics: reactions play once through rest-motion-rest, while states enter a pose, loop the held portion, and exit. It also notes the held-loop requirement for state, though it does not explain failure behavior or side effects on existing animation.
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 and front-loads the key definitions of reaction and state. The trailing word 'free' is cryptic and slightly undermines clarity, but the overall structure is efficient.
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 simple three-parameter mutation with no output schema, the description covers the core behavioral distinction and the state prerequisite. However, it leaves the id parameter unexplained and does not describe what happens when the clean held loop requirement is not met.
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 only 33%, with the clip parameter documented and kind represented by an enum. The description adds substantial meaning for the kind values by explaining reaction versus state behavior, but it does not clarify what the id parameter refers to, leaving part of the low-coverage schema uncompensated.
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 defines what a reaction and a state are in this system, making the tool's classification purpose clear when combined with the name and title. It does not explicitly differentiate from siblings, but no sibling tool appears to perform this classification.
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?
The description gives one important prerequisite: switching to state requires a clean held loop in the clip. It does not explicitly state when to choose this tool over alternatives or what to do if the prerequisite is unmet, leaving usage largely implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.