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

Beyond the annotations it adds real behavior: one token is consumed per call, an XBOSS task is created and its result stored, and the call is not purely read-only. However, destructiveHint=true is never explained (what becomes irreversible when only a draft is written?), and the closing Korean passage is generic boilerplate about "기관 데이터" that does not map onto blog content.

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 first paragraph is front-loaded and efficient, leading with the draft-only scope and then the prerequisite. The second paragraph is templated boilerplate that is partly off-topic for a blog tool and dilutes the otherwise tight opening.

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 mutation tool with a nested required object, no output schema, and destructiveHint=true, the definition covers prerequisites, the no-publish guarantee, and token cost. It still leaves the agent guessing what the call returns (draft identifier? URL?) and what the destructive aspect actually is.

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%, so the nested document fields, the required rights_declared flag, and the account_link_id fallback behavior are already fully documented in the schema. The description only reinforces that document is mandatory ("Naver has no empty-draft step") without adding syntax or semantics not already present, so the baseline 3 applies.

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 states a specific verb and resource ("Creates a new post draft in the connected Naver blog") and explicitly separates draft creation from publication ("Nothing is published - the final publish is done by the customer"), which distinguishes it from the __publish sibling. The one notable omission is that the tool name flags a "retired_api" while the description never mentions deprecation or retirement status.

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 a concrete prerequisite ("Connect the Naver account first") and a clear when-not rule: use this to save a draft, not to publish, because publishing belongs to the customer. It does not route the agent to the __requirements sibling, which appears to exist for pre-flight checks, so alternative selection is only partially resolved.

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