production.physics_inspect_character

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower. The description usefully adds that body/face are preserved and that execution is gated by QA/review, but "fixed physics plan" is unexplained jargon and nothing is said about what happens to candidates when apply=true.

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?

It is short and the scope/effect statements come early, but the copy is telegraphese: a three-way verb, the tool name repeated, and a sentence fragment of internal jargon. It is compact without being clear, so brevity here is not fully earning its place.

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 six-parameter tool that can mutate the scene the description is far too thin: no explanation of candidate selection, what a brief/physics plan is, or the review gate sequence. An agent would have to guess at most inputs.

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% and none of the six parameters carry titles beyond the field name. The description illuminates only one of them ("apply defaults false") and leaves brief, intent, options, physics, and object_name entirely unexplained — insufficient compensation for a 0% coverage schema.

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 uses a triple verb ("Inspect, propose, or execute") and then restates the tool name verbatim, which blurs the core purpose rather than sharpening it. It does add real scope ("isolated secondary candidates", "Body/face preserved") that separates it from primary-deformation tools, but it never names which physics_* sibling it is distinct from.

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; fixed physics plan and explicit QA/review gates" implies a three-stage workflow (inspect → propose → execute behind review gates) and implies that leaving apply=false is the safe inspection path. That usage is only inferred, however — there is no explicit statement of when to pick this over physics_review, physics_accept, or physics_create_candidate.

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