create_world

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

With no annotations, the description carries the full behavioral burden. It adds genuinely useful context: 'dep-safe subset of ~N mods' signals dependency resolution, and 'Does not generate terrain; you create/open the world in-game after apply' clarifies the post-apply side-effect. However, it never discloses the mutating, disk-writing nature of applying a profile, nor any overwrite consequences, which is a notable gap for a creation tool with an overwrite parameter.

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?

Three tight sentences with the primary purpose front-loaded, followed by only high-value additions: dependency safety, the terrain exclusion, and the in-game follow-up. The '~N' placeholder is slightly oblique, but every sentence earns its place with no filler.

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 mutating tool with 8 parameters, no annotations, and no output schema, the description covers the essential mental model well: profile creation, optional mod subsetting, and the post-apply workflow. But it omits return values, failure modes, and overwrite/seed behavior, so an agent would still face uncertainty on edge cases such as re-creating an existing world.

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 only 50% — seed, notes, overwrite, and targetModCount lack schema descriptions. The description partially compensates by tying drop/keep/targetModCount to 'a dep-safe subset of ~N mods', though the literal '~N' placeholder is vague. It adds nothing for seed, notes, or overwrite, leaving those parameters semantically under-specified.

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?

States a specific verb+resource+scope: 'Create a world profile inside the current instance.' The clarification 'Does not generate terrain' prevents confusion with terrain generation, which is a meaningful boundary. However, it does not explicitly distinguish from sibling tools like set_world_mods or apply_world, which overlap in the world-modification space.

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 workflow hint 'you create/open the world in-game after apply' implies this is the first step in a create→apply→play sequence, giving the agent a sense of when to call it. But there are no explicit exclusions or named alternatives, so the agent must infer when to prefer set_world_mods or apply_world instead.

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