分析建築的鏡像對稱程度

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

The description goes well beyond the annotations by disclosing that the tool temporarily writes to the scratch region, backs it up before writing, restores it immediately after comparison, and aborts without modifying the world if backup fails. It also warns that overlapping scratch with the analysis region can destroy the original build and explains the underlying mirror-copy algorithm. This is excellent behavioral disclosure for a tool marked destructiveHint=true.

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 dense but efficient: it states purpose, method, safety behavior, and constraints in a few sentences. It is front-loaded with the primary function and then adds warnings. Slightly longer than strictly necessary, but every sentence carries useful information about behavior or limitations.

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?

The description covers the tool's purpose, scoring semantics, algorithm, side effects, failure mode, safety restoration, overlap prohibition, and size limits. It also explains how asymmetric results are reported at a per-cell granularity. Combined with the output schema and annotations, nothing essential is missing for an agent to invoke this tool 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 coverage is 100%, so the schema already documents all five parameters. The description adds practical semantic value by explaining the roles of the symmetry axes (x/z/xz), the meaning of cellsPerAxis as per-axis subdivisions, and the critical constraint that scratch cannot overlap the analysis region. This extra context helps the agent choose parameter values correctly.

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 states a specific verb ('檢查'), resource (a region/building), and the core function: detecting whether a region is mirror-symmetric and identifying which sub-blocks are not. It also distinguishes the output as a quantitative score (proportion of symmetric cells) rather than a heuristic judgment, clearly differentiating it from a generic region comparison like mc_compare_regions.

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 gives an explicit use case: grading student builds with an objective symmetry score. It also provides important operational conditions, such as scratch must not overlap the analysis region and region size limits. It does not explicitly name alternative tools or state when not to use it, but the use-case guidance is concrete enough for an agent to select it appropriately.

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