production.physics_collision_report

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

Annotations already declare the tool non-destructive, idempotent, and closed-world. The description adds useful context beyond them: apply is off by default, body/face should be preserved, and QA/review gates are enforced. It still does not explain what 'execute' actually changes or what the QA/review gates check.

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?

Three short sentences with no filler, and the apply default and safety gates are front-loaded. The only minor inefficiency is restating the tool name as the resource.

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 six-parameter, mutation-capable tool with 0% schema description coverage, the description is too sparse: it does not document the parameters an agent must supply or the criteria for choosing it over siblings. The output schema covers return values, but the input-side context remains incomplete.

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 coverage is 0% and none of the six optional parameters has a description, so the description carries the full burden. It explains only that apply defaults to false and vaguely references a 'fixed physics plan'; brief, intent, options, object_name, and physics remain unexplained.

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 actions (inspect, propose, execute) and a target ('isolated secondary candidates'), so an agent can infer the general purpose. However, 'physics_collision_report' largely restates the tool name, and the description never explains what the report covers or how it differs from sibling tools such as physics_analyze_penetration or physics_verify_primary_integrity.

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 supplies a default ('apply defaults false') and mentions a 'fixed physics plan and explicit QA/review gates,' implying a gated workflow. But it gives no explicit when-to-use or when-not guidance and names no alternative tool, so selection among the many physics siblings is left to inference.

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