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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint/openWorldHint, yet the description still adds real context: wrong-region calls return 401, an account-registered region always overrides the region argument (region is fixed per account and cannot be mixed), and category_key switches the underlying endpoint. What is missing is anything about result volume or pagination limits beyond what the schema states.

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 content is useful but the anti-pattern warning is a long preamble that pushes the actual purpose statement into the second block, so the definition is not front-loaded by what the tool does. The region and category_key rules are also restated from the schema, adding some redundancy to an already multi-paragraph description.

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 14-parameter read-only list tool with no output schema, the description covers filtering, region selection, sibling handoffs, and the upload_file_key-to-get_content_detail chaining, which hints at response shape. It stops short of describing the returned list envelope or pagination totals, which an agent must infer.

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 explains all 14 parameters, including region and category_key. The description adds only the region decision policy ('사용자 컨텍스트로 결정, 모호하면 확인', account region overrides) and the endpoint branching for category_key, which is modest added meaning over the 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 and resource ('Kollus 계정의 VOD 영상(콘텐츠) 목록을 페이지 단위로 조회한다') and disambiguates the two backing endpoints depending on category_key. It also explicitly hands off adjacent jobs to siblings: single-item lookup to get_content_detail, daily traffic stats to get_statistics_summary_daily, per-video play counts to get_statistics_content_rank.

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?

Gives an explicit anti-use case (polling/setInterval/refetchInterval for CMS or DB mirroring) with the resource to consult instead, then lists concrete recommended scenarios (one-off query, backfill at ops start, user-triggered refresh, debugging). Alternatives for adjacent needs are named by tool, not left to inference.

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