Apply relevant world-state changes

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

No annotations are provided, so the description carries full behavioral burden. It discloses atomicity ('atomically') and durability ('durable entities'), which are critical operational traits. It also explains local refs and forward references, clarifying how changes can reference each other. Missing details like failure modes or rollback behavior are partially covered by atomicity, but not fully elaborated. Overall, it provides enough behavioral context for safe invocation.

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?

Two sentences, both dense with information. Key operational details (atomicity, refs) are front-loaded, followed by usage guidance. No wasted words; every clause earns its place. Ideal conciseness.

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 complex batch tool with three action types and nested object schemas, the description covers the essential operating contract: atomicity, refs, and appropriate usage. It does not mention the 100-item limit or the eventSecret secret-entity rule, but those are schema-encoded. Given the schema's richness and the description's focus on behavior, it is sufficiently complete for an agent to understand the tool's purpose and constraints, though a note on error handling would elevate 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 covers 75% of parameters (summary, worldId, eventSecret have descriptions; changes does not). The description adds a nuance about local refs and forward references beyond the schema's generic ref mentions. However, it does not specify how 'changes' should be structured overall, and the schema already documents most parameter semantics. The added value is marginal but non-zero.

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 the action (create, update, delete) and resource (durable entities) performed atomically in one call. It distinguishes itself from sibling tools like update_world or create_checkpoint by emphasizing batch atomicity and multi-entity support. The verb-resource pair is specific and 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 guidance on when to use the tool: 'Store only lasting or story-relevant changes, preferably together at natural story boundaries.' This implies batching at narrative milestones and filtering for durable changes. However, it does not explicitly name alternative tools or state when NOT to use it (e.g., for single-entity updates), leaving some inference to the agent.

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