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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered by structured data. The description contributes that the lookup is free of charge and that it returns guidance-level metadata (purpose, tone, required items, criteria) rather than documents themselves. It says nothing about result count, format, or whether an empty query returns everything, which is the sort of detail that would raise this score.

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 core sentence is appropriately short and front-loaded, but the trailing '무료. [무료]' repeats the same claim twice and reads as leftover template markup. It is brief without being wasteful in the main clause, yet the tail is pure noise.

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 one-parameter read-only search with no output schema and a fully documented parameter, the definition covers what is searched and that it is free. What is missing is the relationship to the similarly named sibling tool and any hint of the shape of returned results, which matters for a lookup tool an agent must decide to call.

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 is 100% and the single 'query' parameter is documented in the schema as a title/purpose search term. The description implies keyword-style searching over template attributes but adds no syntax, language, or matching-behavior detail beyond the schema. Baseline 3 applies when the schema carries the parameter semantics.

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 gives a concrete verb (검색합니다) and a specific object: the purpose, tone, required items, and writing criteria of core templates. That is more than a restatement of the name 'document_templates'. However, it never distinguishes itself from the near-identical sibling 'document_template' (singular), so an agent cannot tell the two apart from the text alone.

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?

There is no statement of when to use this tool versus alternatives, nor any prerequisite or exclusion. Given siblings named 'document_template', 'document_assist', and 'document_ai_write', the absence of any routing guidance is a significant gap. The only contextual note is '무료', which is not usage guidance.

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