Agent 感測周遭

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

The description reinforces the non-destructive nature ('不改變世界') and adds specifics beyond the annotations: inspect returns block type, inspectData returns data values, detect checks for solid blocks, and detectRedstone checks redstone signals. These details align perfectly with readOnlyHint/idempotentHint and provide actionable behavioral expectations.

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 with no fluff. It front-loads the core purpose and safety property, then efficiently enumerates the modes, ending with a memorable usage metaphor. Every sentence earns its place.

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?

Given the availability of an output schema and comprehensive annotations, the description covers all necessary context: what each mode does, that it is non-destructive, and when to use it. For a sensing tool with two enum parameters and no required fields, nothing critical is missing.

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?

With 0% schema description coverage, the description takes on full responsibility for explaining the mode parameter. It explicitly defines each enum value, which is the critical parameter. The direction parameter values (forward/back/left/right/up/down) are self-explanatory standard directions, so no additional description is needed.

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 tool reads the Agent's surroundings and does NOT change the world, listing four specific sensing modes (inspect, inspectData, detect, detectRedstone) with distinct purposes. This differentiates it from action-oriented siblings like mc_agent_act or mc_agent_move, making the tool's role 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 phrase '這是 Agent 的「眼睛」，行動前先看' provides clear context: use this tool as a pre-action sensing step. While it doesn't explicitly compare against alternative read tools like mc_read_block or mc_query_target, it establishes a clear usage heuristic and when to invoke it (before acting).

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