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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered and the description's real contribution is the negative-space list: DRM policy details, callback URL, playback expiry, subtitle tracks and encoding profiles are NOT returned. That is genuinely useful for an agent deciding whether this tool answers its question. However, it does not say what happens on a missing/inaccessible key (only that wrong region yields 401) nor whether a tombstoned or untranscoded item still returns a body, which matters for a lookup tool with no output schema.

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?

Purpose is front-loaded and the not-included list earns its space, but the response-field enumeration is a long inline run of field names that could be compressed, and the region paragraph restates what the schema already says about defaults and ambiguity. Dense but with real redundancy against structured fields.

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 two-parameter read with no output schema, the description supplies the return-value inventory and the explicit exclusions, so an agent knows what it will and won't get back. Remaining gap is error/empty-case behavior (nonexistent key, still-transcoding item) on a tool where the annotation set is otherwise complete.

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 both parameters are richly documented, so the schema carries most of the weight. The description still adds meaning not present in the schema: the account-level region always wins over the 'region' argument and mixed regions per account are impossible, which changes what passing 'region' actually does. The upload_file_key vs media_content_id vs content_id disambiguation is largely duplicated from 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?

Opens with a specific verb+resource in one line ('특정 영상 1건의 메타데이터를 조회한다') and pins it to the endpoint GET /media-contents/{upload_file_key}. It explicitly contrasts with the sibling list_media_contents ('응답 필드는 list_media_contents 항목과 같은 구조'), so an agent can separate single-item fetch from list without opening either schema.

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 concrete use cases (트랜스코딩 실패·암호화 여부·파일 속성 1차 확인) and an explicit fallback: if upload_file_key is unknown, start from list_media_contents. Region selection adds an escalation rule — decide from user context, ask the user when ambiguous, never guess — plus the exclusion case where account-registered region overrides the argument.

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