case_stats

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

With no annotations provided, the description fully carries the burden. It discloses that the tool reads a pre-computed snapshot (not real-time), that n_cases is capped per province and not actual case count, that win_rate is always null, and that province dimension has excluded malformed entries. The n_cases_capped flag is also mentioned.

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 relatively long but efficiently structured. It front-loads the main purpose, then lists caveats with numbered bullet points for clarity. Every sentence adds necessary context; no waste given the complexity. Could be slightly more concise but appropriate.

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 one parameter, no output schema, and no annotations, the description is remarkably complete. It covers what the tool does, the output fields (n_cases, p25/median/p75, average salary), data freshness, and critical caveats about sampling and capping. It also relates to sibling tools for context.

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% for the single parameter dimension, but the description adds significant meaning beyond the enum values. It explains what each dimension represents (e.g., province→省份, term_reason→解雇原因) and provides context for the output statistics. This extra value justifies a score above the baseline of 3.

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 returns aggregated statistics on labor dispute cases sliced by dimension. It specifies the tool reads a pre-computed snapshot, not the full database, which distinguishes it from siblings like case_analytics. The verb '回傳聚合統計' and resource '勞動爭議判例' are specific.

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 explicitly states when to use this tool vs alternatives. It warns that the snapshot is not consistent with other tools, so numbers should not be compared. It directly points to case_analytics for real case counts. It also advises against using n_cases for cross-province comparison due to capping.

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