Scan surrounding Minecraft blocks to find positions of a named block type, or return block statistics when no name is provided.
扫描我周围方块：给 name 就找这种方块的位置；不给就返回方块统计。
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | 可选：只找这种方块（如 oak_log） | |
| limit | No | name 模式下最多返回几个（默认 10） | |
| height | No | 垂直范围 ±（默认 4，上限 16） | |
| radius | No | 水平半径（默认 16，上限 48） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral burden. 'Scan' implies a read-only, non-destructive operation, but the description never states that explicitly, nor mentions cost/performance tied to radius and height limits.
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 compact clauses, mode-switching condition front-loaded, zero filler. Every phrase carries information.
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 4-parameter, no-annotation, no-output-schema read tool, the description plus full schema coverage is close to sufficient. The gap is that it doesn't explicitly confirm the operation is safe/read-only, which an agent must currently infer from the verb.
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%, so the baseline is 3; the description earns extra by documenting cross-parameter semantics the schema does not — that presence of 'name' switches the tool into a positions-lookup mode and changes what 'limit' means. The remaining defaults and caps are already in 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?
States a concrete verb and resource ('扫描我周围方块') and distinguishes two output shapes: block positions when a name is given, block statistics otherwise. It doesn't name the nearest sibling (mc_observe / mc_dig), so differentiation from those tools is left to inference.
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 conditional clause ('给 name 就…不给就…') gives clear in-tool mode selection, which is real usage guidance. However it never says when to pick this over mc_observe or mc_dig, and gives no prerequisites such as being connected or in-world.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.