production.physics_cache_plan

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

Annotations already declare destructiveHint=false, readOnlyHint=false and idempotentHint=false, lowering the bar. The description still adds real behavioral context: it operates only on isolated secondary candidates, preserves body/face, defaults to non-applying (safe preview), and enforces 'explicit QA/review gates'. It does not say what state changes on apply=true or how failures/rollbacks behave, so it is useful but incomplete for a mutating tool.

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?

Short and front-loaded with the mode list, but the trailing clause 'fixed physics plan and explicit QA/review gates' is a cryptic fragment that reads as jargon rather than a directive, and 'apply defaults false' partially duplicates the schema default.

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?

An output schema exists so return values need not be described, but for a 7-parameter, mutation-capable planning tool with zero schema coverage and strong sibling overlap, the description omits the key differentiators and parameter meanings an agent needs to invoke it correctly.

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 7 parameters, so the description must carry the burden and it does not. It only clarifies 'apply' (default false) and alludes to a 'fixed physics plan'; parameters like brief, intent, options, physics, object_name and operation_id are unexplained anywhere.

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 gives a tri-modal verb set (inspect/propose/execute) that is genuinely more informative than the bare name, and it scopes the target to 'isolated secondary candidates' with 'Body/face preserved'. However, the resource is restated as the tool's own name ('physics_cache_plan'), and it never distinguishes this from close siblings such as production.physics_plan or production.physics_bake_cache, leaving the agent to guess which cache-planning tool to pick.

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?

'apply defaults false' implies a dry-run-first workflow, which weakly hints at when to use the inspect vs execute mode. Beyond that there is no explicit when-to-use, when-not-to-use, or named alternative among the many physics siblings (physics_plan, physics_plan_hair, physics_bake_cache), so selection guidance is essentially absent.

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