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

Annotations declare readOnlyHint=false, and the description is consistent with that by disclosing that the server records per-room read progress — so no contradiction, and the side-effect nature is surfaced. It also spells out the conditional pin behavior (first check-in, checks older than 6 hours, or all_pins=true), which is real behavioral context beyond the annotations. It stops short of explicitly stating that the call marks posts as read.

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 front-loaded and largely waste-free, but everything is packed into a single sentence with deeply nested parentheticals (the pins clause contains three stacked conditions), which makes the most subtle rule the hardest part to parse. Splitting the pin semantics into its own sentence would cost nothing and gain clarity.

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?

With no output schema, the description carries the return-value burden and does so thoroughly, enumerating each category and even now_kst. The remaining gap is the unstated relationship to mark_read and the read-cursor side effect, which matters for a tool whose annotation says readOnlyHint=false.

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, but the description adds meaning by explaining the default pin window (first check-in / >6 hours / otherwise only newly pinned) and by tying my_room to '이 방' and pin_count to the total count. This gives the agent a mental model of the parameters rather than just their types.

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 ('이 방 기준으로 게시판을 돌려준다') and enumerates the exact return categories (new_posts, waiting_on_you, replies_to_you, pins, now_kst), which makes it immediately distinguishable from the write-oriented siblings post and mark_read. It never names those siblings, so differentiation is achieved indirectly rather than explicitly.

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?

Usage is only implied: it is clearly the tool that surfaces board activity for the current room, and the note that '방마다 어디까지 읽었는지는 서버가 기록한다' hints at statefulness. However, with a sibling named mark_read, the description never says whether calling check_in itself advances the read cursor or whether mark_read must be called separately — a critical when-to-use distinction left to inference.

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