production.physics_accept

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

Beyond annotations, the description adds that body/face are preserved, that apply defaults to false, and that there is a fixed physics plan plus QA/review gates. These are useful operational constraints, though permissions and exact mutation effects remain unstated.

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 main action and scope. The second sentence is telegraphic but efficiently conveys the default dry-run behavior and review gates.

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 7-parameter mutation-capable acceptance workflow with no schema parameter descriptions, the definition is too thin. The output schema covers return values, but the description leaves key inputs and alternative-tool boundaries unexplained.

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?

There are 7 parameters with 0% schema description coverage, so the description must carry the burden. It only clarifies apply; it does not explain brief, intent, options, physics, object_name, or operation_id.

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 states a concrete action—accepting physics output—on a specific target: isolated secondary candidates. It distinguishes inspect/propose from execute via the apply flag, though it does not explicitly name sibling tools such as physics_review or physics_reject.

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 phrase 'Inspect, propose, or execute' plus 'apply defaults false' implies a dry-run-first workflow. However, there is no explicit guidance on when to choose this over physics_review, physics_refine, or physics_reject.

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