unreal_workflow_apply

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

Annotations say destructiveHint=true and idempotentHint=false, but the description goes beyond: it specifies no auto retry, notes partial application on timeout (must inspect receipt), explains undo behavior per change type, and warns about visual capture for material/light. This is critical for safety and not in annotations.

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?

Four concise sentences, each imparting necessary operational detail. Front-loaded with the core action and return format, then safety and failure handling. No wasted words; fully justified.

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?

Given complexity (destructive, non-idempotent, side effects) and rich output schema, the description covers the key points: single application, partial failure, side effects on undo, and post-conditions for capture. Minor gaps: doesn't specify how to interpret before/after state format, but output schema likely handles that.

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 has only one parameter (plan_id) with zero description coverage, so the description should add meaning. It mentions 'domain plan' which implies plan_id refers to a plan, but doesn't spell out the type or format (e.g., UUID vs name). Lacks explicit correlation but is acceptable given single param.

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 it applies a 'reviewed domain plan once' and returns before/after state, making the core action clear. It distinguishes itself from siblings like unreal_workflow_preview (preview vs apply) and unreal_apply (another apply tool), though it doesn't explicitly name them.

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 provides context for when to use: after a plan is reviewed, and notes no automatic retry. It doesn't explicitly mention alternatives, but the 'reviewed' qualifier implies it should be used only on reviewed plans, and bad outcomes route to unreal_workflow_receipt. Missing explicit when-not-to-use.

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