Scene

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does state that the tool manages the active scene and can perform mutations (set, directive, presence, autonomy, choices, oracle). However, it does not disclose side effects, whether existing scene data gets overwritten, or what the agent can expect back from oracle resolution. The mutation is implied but not explicitly characterized.

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 three sentences, front-loaded with the core purpose, followed by scoped use cases and a clear exclusion. Every sentence earns its place, there is no fluff, and the structure makes scanning easy.

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?

The tool is complex (23 parameters, 7 enums, nested objects, no output schema), and the description provides a strong high-level orientation: what it does, when to use it, and when not to. It does not explain behaviors like fast_forward or autonomy levels, but those are documented in the schema. The only notable omission is that it doesn't explicitly state that the 'action' field selects one of these operations, though the 'or' phrasing implies it.

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 100%, and every parameter already has a description with the action category in parentheses (e.g., '(set)', '(oracle)'). The description groups these categories into use cases like 'setting scene state (description, location, type)', but adds no new syntax, value constraints, or behavioral meaning beyond what the schema already documents. Baseline 3 is appropriate.

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 uses a specific verb ('Manage') and resource ('the active scene and its narrative framing'), then enumerates the concrete actions it supports: setting scene state, narrative directive, party presence, AI autonomy, choices, and oracle rolls. It explicitly differentiates from the sibling 'story' tool by stating when NOT to use it ('recording a story beat — use story (action: record)').

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 states 'Use when' with specific scenarios mapped to the tool's action types, and 'Do NOT use when' with the exact alternative tool and call ('story (action: record)'). This gives an agent clear routing criteria both for and against this tool.

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