production.physics_reject

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

Annotations already cover safety profile (non-destructive, not idempotent), and the description adds useful context: 'Body/face preserved', 'apply defaults false', and 'fixed physics plan and explicit QA/review gates'. However, it doesn't explain what rejection actually does (e.g., marks as rejected vs deletes) or what happens to the candidate.

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 concise and front-loads the main action, but the three fragments are somewhat disjointed and could be better organized.

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 tool with 7 parameters and zero schema descriptions, the description is inadequate—it doesn't explain key parameters or the operational meaning of rejection. The presence of an output schema reduces the need for return-value details, but critical gaps remain.

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 the description provides no explanation of any parameter beyond repeating the default for 'apply'. Parameters like brief, intent, options, physics, object_name, and operation_id are completely undocumented.

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 'reject on isolated secondary candidates' which gives some context, but 'Inspect, propose, or execute' is confusing and it doesn't clearly distinguish from siblings like physics_accept. The core action 'reject' is not explained operationally.

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 implies usage via 'apply defaults false' and mentions QA/review gates, but gives no explicit when-to-use versus alternatives (e.g., physics_accept or physics_review). No exclusions or prerequisites are clearly stated.

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