Scene

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

The description only says 'manage' without specifying side effects, such as overwriting existing scene state or interacting with other systems. The annotations (readOnlyHint=false, openWorldHint=true) imply mutation, but the description adds no concrete behavioral details beyond that, leaving the actual state-changing effects vague.

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, using a single sentence plus a compact list of use cases and a negative directive. It avoids redundancy and is well-structured for quick parsing.

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 the tool's complexity with 23 parameters, nested objects (e.g., fast_forward, choices), and multiple actions, the description is far too brief. It does not explain the semantics of the many actions (e.g., what 'autonomy' or 'oracle' entails) nor how to properly construct nested objects, leaving the agent without enough context to use the tool effectively in all cases.

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?

Although the schema covers 100% of parameters, most descriptions merely repeat the parameter name or enum list (e.g., 'Safety tier (autonomy)' or 'set, directive, presence, autonomy, choices, or oracle.'). They add little semantic value beyond the schema's type and enum definitions, failing to explain what each parameter actually means or how it influences tool behavior.

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 clearly states it manages the active scene and its narrative framing, enumerating specific use cases like setting scene state, directives, presence, autonomy, choices, and oracle rolls. It explicitly distinguishes from the story tool (recording beats), making the purpose unambiguous.

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 description provides explicit 'Use when' and 'Do NOT use when' guidance, directing users to the story tool for recording beats. This clearly delineates when to select this tool over its primary sibling, satisfying the usage guideline requirement.

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