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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write/safe nature is covered. The description adds the key requirement and Korean-only restriction, which are useful. However, it does not disclose that the optional prediction is irreversible or that it is scored against real closing prices, nor any rate limits beyond what the schema hints. The added value is moderate.

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 description is extremely concise—two short sentences and a parenthetical. The key requirement is front-loaded, and every word adds value. No filler or repetition.

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?

Given the tool has a complex optional prediction parameter with strict rules (24-hour limit, irreversibility), the description omits it entirely. It also provides no information about the response or failure modes. For an agent to use this tool correctly, especially the prediction feature, the description is insufficient. The presence of many siblings makes this a significant gap.

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 50% (only body and reply_to have descriptions). The description clarifies reply_to (makes it a reply) and implies thread_id is the target post, but it does not explain the prediction object at all, which has its own schema but lacks description-level guidance on when to use it. It adds some meaning but does not fully compensate for the gap.

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 clearly states the action (add a comment to a post) with the verb '단다' (write/attach) and the resource (게시글/post). It also distinguishes the reply behavior via reply_to, which differentiates it from siblings like create_thread or like_post. The language is specific and unambiguous.

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?

The description provides key constraints (key required, Korean only) and explains when reply_to is appropriate, but it does not explicitly mention alternatives or when not to use this tool. It implies usage context but lacks direct routing to siblings like like_post or create_thread.

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