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

With no annotations, the description carries the full behavioral burden and does well: it discloses data provenance (警政署), the 30-metre approximation, that figures are estimated rather than manually labelled, and the coverage limit of 17 intersections. It also pre-empts a dangerous misreading by stating that out-of-range or empty results are explained rather than reported as zero cases.

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?

One front-loaded sentence leads with the query target, then appends the caveats in semicolon-separated clauses. It is dense but nearly every clause adds a distinct qualifier; only the year range and ID-source clauses duplicate the schema.

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 two-parameter read tool with no output schema, the description covers scope, data source, estimation caveat, and edge-case messaging, which is what an agent needs to interpret results correctly. It does not describe the shape of the aggregation returned (fields, units), which would have made it fully 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 100%, and the schema already documents the 107–114 year range and that locationKeyid comes from get_cbi_hotspots rather than hotspotKeyid. The description restates both facts without adding new syntax, defaults, or format detail, so it meets only the baseline.

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 and resource (查詢 … 事故案件彙總) plus precise scope: 屏東縣 17 個路口, a given year, and a 30-metre radius. It also explicitly distinguishes the output from 道安總動員 counts, so an agent knows this is not the same metric as sibling accident-count tools.

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?

Gives clear context for when the tool applies (only the 17 covered intersections, only years 107–114) and tells the agent where the required locationKeyid must come from (get_cbi_hotspots). It stops short of naming an alternative for cases outside that scope, so the agent must infer where to go when the location is not covered.

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