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

Annotations already cover read-only/idempotent/open-world, so the bar is lower, and the description still adds behavior the annotations don't: a hard Korean-language input constraint, the id-extraction convention for chaining into get_document, and the caveat that decisions and interpretations are reference material rather than law. It omits result volume, ranking, and pagination behavior beyond the schema's page field.

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 purpose is front-loaded and the grouping with English glosses helps an agent pick a source value, but roughly half the text is a near-duplicate of the enum that is already fully described in the schema. A long inline enumeration of ~50 agencies makes the definition heavy for the marginal selection value it adds.

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?

With no output schema, the description carries the burden of explaining results, and it does supply the one thing an agent needs to chain calls (the id is the first number of each result). Combined with the source taxonomy and language constraint, that is close to complete for a four-parameter search tool; pagination behavior is the main gap.

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 100%, so the schema already documents query, source, page, and body_search; the description is required to do little. The description's source taxonomy largely restates the enum (though it usefully groups it and glosses the Korean names in English), and it adds only the Korean-language constraint on query — it never mentions body_search or page.

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 first sentence gives a clear verb plus resource ("Search Korean decisions, interpretations and other materials (법제처) by keyword") and the bulleted source taxonomy makes the scope concrete. It partially differentiates from siblings by routing 국세청·재정경제부 queries to search_tax_interpretation and result retrieval to get_document, but it never explains how it relates to the overlapping search_case and search_interpretation tools.

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?

It gives real usage context: pick the material via `source`, queries must be in Korean except for 영문법령, and the first number of each result is the id to pass to get_document — a concrete follow-up workflow plus one explicit exclusion. It stops short of stating when to prefer this over search_case or search_interpretation, which appear to overlap heavily.

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