production.physics_generate_soft_secondary

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

Annotations already establish that this is a non-read-only, non-destructive, non-idempotent, closed-world operation. The description adds useful behavioral context beyond that: apply defaults to false, the physics plan is fixed, QA/review gates are explicit, and body/face are preserved. The remaining ambiguity about what 'fixed physics plan' means keeps it from a top score.

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 two short sentences with no wasted text, and the operational mode and default apply behavior are front-loaded. The fragmentary phrasing ('apply defaults false') is terse but still understandable.

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?

This is a complex tool with seven undocumented parameters, many sibling tools, and no schema descriptions. The output schema means return values need not be explained, but the description still leaves too much unsaid about parameter meanings and when this tool is preferred over the many other physics generation and secondary-motion siblings.

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 needs to carry parameter meaning, yet it only addresses one of seven parameters (apply defaults false). Nothing is said about brief, intent, options, physics, object_name, or operation_id, leaving the agent with no semantic guidance for most inputs.

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 names three modes (inspect, propose, execute) and scopes the work to isolated secondary candidates while preserving body/face, which gives some concrete purpose. However, it largely restates the tool name and never explains what 'soft secondary' physics actually covers, so it does not clearly distinguish itself from siblings such as physics_generate_secondary_bones, physics_generate_hair_secondary, or physics_bake_secondary_motion.

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 implies when to use the tool through its inspect/propose/execute modes and the note that apply defaults to false, plus mention of QA/review gates. But it gives no explicit when-to-use versus alternatives and no exclusion criteria, leaving the agent to infer selection from the mode wording alone.

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