law_search

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

Even with readOnlyHint and openWorldHint annotations, the description adds crucial behavioral context: query cannot be empty or it returns the entire catalog, max_records has no upper bound and can fetch everything, page_size caps at 500, and allow_full_catalog only works with query="*". These are non-obvious behaviors an agent must know before calling.

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 structured as a compact Args list where every line adds value. It is longer than a one-liner but justified by needing to document 6 parameters and several hidden constraints; there is no redundancy or filler.

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 6-parameter search tool with no output schema, the description covers target codes, query constraints, pagination, scoping, and the full-catalog escape hatch. It leaves a few opaque target abbreviations (eflaw, elaw, lsStmd) undeclared, but compensates by referencing law_targets. The lack of any return-type description is a minor gap given the tool's straightforward search nature.

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 carries the full burden, and it excels. Every parameter is explained with valid values, defaults, constraints, and cross-parameter relationships — e.g., allow_full_catalog requires query="*", and target values are enumerated with real code examples.

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 opens with '법령·판례 등 한 갈래를 검색한다' — a specific verb (search) applied to a resource (one branch of statutes/precedents). It lists the exact target codes and scope options, making it unmistakably distinct from sibling tools like law_status or law_body.

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 clearly explains when to use the tool (searching a single branch), and it points to law_targets for the full target list, which helps agent routing. It does not explicitly name alternative sibling tools or say when not to use this tool, so it falls short of full exclusion guidance.

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