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

No annotations are supplied, so the description carries the full burden, and it does disclose relevant behavior: the data is a read/aggregation of hotspot causes, a multi-year trend back to 民國 106, and one year's accident positions. It also guarantees the rowRef is pre-composed of kind, hotspot code and location code so mismatched lookups cannot occur. The gap is the deferred constraint "事故位置的限制同 get_location_accident_points", which forces the agent to consult another tool for the actual limitations.

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?

A single dense sentence, front-loaded with the purpose, then the returned components, then the identifier provenance rule. Despite the semicolons no clause is redundant and nothing is buried.

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 no output schema, the description does the work of describing returns by naming the three result blocks, and it covers both parameters fully. Completeness is slightly reduced by outsourcing the accident-position caveats to get_location_accident_points rather than restating them.

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, and the description adds real meaning on top: it explains that rowRef must come from the same row of get_cbi_hotspots and that the compound string encodes kind plus hotspot and location codes, which explains the regex pattern. It also frames the valid year range as 民國 106 onward.

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 specific verb (查詢) and resource (單一路口或路段的概況) and enumerates the three blocks returned (肇因與碰撞類型分布、歷年件數趨勢、某年度事故位置). That enumeration distinguishes it from the single-purpose siblings like get_location_trend and get_location_accident_points, though it never says so outright.

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?

Usage is clear: one call per location, with year and a rowRef taken from the same row of get_cbi_hotspots. The prerequisite and the sourcing rule for the identifier are explicit. There is no explicit when-not statement (e.g. for multi-location comparison use another tool), but the single-location framing is unambiguous.

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