Agent 背包操作

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

Annotations are all false, so the description carries the burden. It reveals the direction relativity (important behavior) and lists actions, but it does not disclose consequences like whether dropping items removes them permanently or places them in the world, nor does it mention error handling or side effects. The term '清空整槽方向' is ambiguous about what happens to the items. Some transparency is provided, but significant gaps remain.

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 concise (two sentences) and front-loads the action list. It avoids redundancy, though the first sentence is a long enumeration that could be structured more cleanly. Overall it is efficient and effective.

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?

With an output schema present, the return format is known. The description includes the prerequisite, direction semantics, and action list, covering key aspects for a multi-action tool with 5 parameters. It lacks discussion of error cases, permissions, or detailed side effects, but given the output schema and clear prerequisite, it is reasonably complete.

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 80%, which provides baseline, but the description adds value by mapping actions to parameters (e.g., 'count 查槽內數量') and clarifying that direction is relative to Agent's facing, not world orientation. This goes beyond the schema's enum listing. It also explains the necessity of mc_agent_create, aiding parameter interpretation.

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 specifies the tool operates on the Agent backpack with a clear list of actions (count, space, detail, drop, dropAll, transfer), each with a brief meaning. It also explicitly states a prerequisite (Agent must be summoned with mc_agent_create) and clarifies a key distinction from world coordinates (direction relative to Agent's facing). This is a specific verb+resource description that differentiates it from siblings like mc_agent_act or mc_agent_move.

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 clearly states the prerequisite of using mc_agent_create and defines the tool's scope as Agent backpack operations. However, it does not explicitly mention when not to use it or name alternative tools for similar tasks. It provides clear context for invocation but lacks explicit exclusions.

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