law_search

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

Annotations indicate read-only, idempotent, and non-destructive behavior, which the description doesn't contradict. The description adds valuable context: it specifies the API doesn't support JSON (only HTML/XML), recommends display settings for optimal results, and clarifies the date format (YYYYMMDD). This goes beyond what annotations provide about safety and idempotency.

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 well-structured with a clear purpose statement, parameter explanations in a bullet-like format, and a returns section. It's appropriately sized for a 9-parameter tool. Minor improvements could include bolding key constraints like 'JSON not supported' for faster scanning.

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 search tool with 9 parameters, 0% schema coverage, no output schema, and read-only/idempotent annotations, the description provides strong coverage. It explains all parameters, notes API format limitations, gives usage recommendations, and clarifies the date format. The main gap is lack of output format details, but given the annotations indicate safe operation, this is acceptable.

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?

With 0% schema description coverage, the description carries full burden for parameter documentation. It successfully explains all 9 parameters: query (search keyword), display (results per page with recommendation), page (page number), oc (OC override), type (response format with constraints), sort (sort order), date (announcement date with format), org (ministry filter), and knd (law type filter). The only gap is lack of enum values for sort, org, and knd.

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 searches Korean laws by announcement date, specifying the resource (Korean laws) and scope (by announcement date). It distinguishes itself from siblings by focusing on current laws rather than administrative rules or other legal documents, though it doesn't explicitly compare to each sibling tool.

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 implies usage for searching current Korean laws by announcement date, with a recommendation to use higher display values (50-100) for law searches. However, it doesn't explicitly state when to use this tool versus alternatives like 'law_service' or 'eflaw_search', nor does it provide exclusion criteria or prerequisites for use.

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