預覽幾何建造

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

Annotations already cover readOnlyHint=true and idempotentHint=true. The description adds specifics: it reports block count, bounding box, and fill command count, and emphasizes absolute world coordinates. This goes beyond the annotations without contradicting them.

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 with zero waste. The purpose is front-loaded, the coordinate caveat and tool suggestion are concise, and no irrelevant detail is included.

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 preview tool with an output schema, the description adequately covers use, output highlights, and a coordinate prerequisite. It doesn't mention volume limits or edge cases, but those are likely in the output schema. It is sufficiently complete for an agent to call correctly.

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 description coverage is 67% and the schema already documents shape variants and block states. The description adds no parameter-specific guidance (e.g., how to choose shape kind), so it stays at baseline without compensating for the uncovered parts of the schema.

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 opens with '只計算不動工' (only calculate, don't build), a specific verb+resource that immediately distinguishes it from building tools. It then lists concrete outputs: block count, bounding box, and number of fill commands. This clearly differentiates it from siblings like mc_build_shape and mc_blueprint_preview.

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 instructs to use mc_query_target when the player's location is unknown, and recommends using this preview tool before any build that changes the world. However, it doesn't explicitly name the building sibling (mc_build_shape) or state when NOT to use it, leaving some inference.

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