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

The description opens with 'Read-only' while the annotations declare readOnlyHint=false, and the description later contradicts itself with '이 호출은 순수 읽기 전용이 아닙니다' (this call is not purely read-only). It also asserts 'No credential or login required' and then immediately discusses authenticated calls. The trailing Korean boilerplate about per-call token consumption and XBOSS task creation is unrelated to a requirements-lookup and actively confuses the safety profile.

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 useful content (the list of required inputs) is buried between idempotency boilerplate and a block of Korean text about token exhaustion and institutional data changes that has no apparent connection to this tool. The opening 'Read-only' claim is contradicted 100 words later, so the structure is not just verbose but misleading.

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 requirements-lookup tool with no output schema, the description does enumerate the inputs an agent must supply, which is the core need. It omits any indication of which sibling tool to call after satisfying the requirements, and the contradictory read-only/token/XBOSS statements leave the agent uncertain about what this call actually does.

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 baseline is 3. The description does add genuine semantics beyond the schema — reuse the key only to recover a lost response, generate a new key for a new execution, and do not confuse it with a provider-specific idempotency_key — but this is tangled with an unrelated claim that the key is unavailable to anonymous calls, which conflicts with the stated no-credential nature of the tool.

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 concrete deliverable: it 'Returns what you must provide to save a draft to Tistory' and enumerates the fields (content artifact reference, post title, optional tags and category, rights declaration). That is specific enough for an agent to know this is a discovery/requirements call rather than an execution call. It does not, however, distinguish itself from the sibling create/publish/update tools that consume those requirements.

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 when-to-use guidance relative to the sibling tools (create, publish, update), nor any statement of what an agent should do with the returned requirements. The only conditional text concerns the idempotency key ('For an authenticated call...'), which is parameter mechanics rather than tool-selection guidance.

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