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

Annotations cover readOnly and openWorld (false), but description adds that it returns links like citations and related cases, which is useful behavioral context beyond annotations.

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?

Bilingual, concise: one sentence in Korean, one in English, both front-loading purpose and output. No wasted words.

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?

Complete for a read-only single-article fetch: purpose, output (full text + links), and key format/source are all stated. No output schema needed.

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 100% and schema documents the key parameter. Description adds that key comes from search_law/search_procurement results, providing provenance not in schema.

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: fetch full text and links of one statute article. Distinguishes from siblings by implying a single article vs search_law/search_procurement which find multiple.

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?

Describes output includes full text and links (citations, delegations, related cases). Does not explicitly say when to use vs alternatives like get_law, but the context of one article vs entire law is clear.

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