production.animation_refine_balance

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

Beyond annotations, the description discloses meaningful behavior: a plan-first workflow with apply defaulting to false, generation as an immutable plan.json reference, source Actions being retained, and unsupported adapters returning concrete errors. These details add real context about side effects and error behavior, though the jargon reduces clarity.

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 poorly structured, front-loaded with the unhelpful phrase "high-level M6 unit" and dense with jargon. Several sentences (e.g., about technical QA vs. artistic review) do not clearly connect to invoking the tool.

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 mutation tool with 7 parameters and no schema documentation, the description is incomplete: it omits most parameter meanings and does not clarify the required mapping or rig compatibility in actionable terms. The output schema covers return values, but the input side remains underspecified.

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?

With 0% schema description coverage across 7 parameters, the description is the only source of parameter meaning. It partially covers apply, generation, and options, but leaves brief, intent, object_name, and operation_id completely unexplained, and does not describe the expected structure of the object parameters.

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 never plainly states what "refine balance" does beyond restating the tool name with opaque jargon like "high-level M6 unit." It implies a plan/apply workflow for balance refinement but does not define the operation (e.g., adjust center of mass, posture) or distinguish it from siblings such as animation_analyze_balance or animation_refinement_plan.

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 some procedural guidance: "Plan first, apply=false by default" and prerequisites like "Explicit mapping and compatible body rig required." However, it does not say when to choose this over animation_analyze_balance or animation_refinement_plan, nor does it state exclusions or alternatives.

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