search_interpretations

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

No annotations are provided, so the description carries the full behavioral burden. It discloses useful non-obvious behavior: results include case_id for chaining, and include_old only takes effect when year=0 (>0 restricts to 新制憲判字). It does not state result ordering, pagination, or behavior on empty keyword, so it falls short of a 5 for a 7-parameter read tool.

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?

Front-loads the purpose and the sibling routing in the first two sentences, then lists args compactly. The Args block is long but each line carries distinct semantics; only mild redundancy from restating defaults already in 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 parameter-heavy tool with no output schema and no annotations, the description covers scanning scope, filtering semantics, defaults, and the chaining contract. Weakness: it says results carry case_id but not what other fields come back or how results are ordered/limited in practice.

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 description coverage is 0%, so the description must compensate entirely, and it does: every one of the 7 parameters is defined, including the match fields for keyword (標題/字號/爭點/理由書全文), the 民國 year convention, the 0=不篩選 sentinel, inclusive number_from/number_to, the include_old/year interaction, and the max_results default.

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+resource (列舉大法官解釋/憲法法庭裁判) and the search scope (關鍵字全文搜尋 covering 爭點 + 理由書). It also names the sibling it is not (行政機關的函釋、解釋令 → search_agency_interpretations), so an agent can separate it from the other interpretation tools without opening schemas.

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?

Explicitly gives the when-not case ('行政機關的函釋、解釋令不在這裡，用 search_agency_interpretations') and the downstream contract ('每筆結果帶 case_id，可直接傳給 get_interpretation()'), routing the agent to both the correct alternative and the natural next call.

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