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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is free. The description adds genuinely new facts beyond them: no API key is required and the tool is designed for repeated short-interval polling with a cursor, which tells an agent how to behave operationally.

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?

Four short sentences, front-loaded with purpose then polling behavior then auth. The English parenthetical duplicates the Korean opening almost verbatim, which is mild redundancy but arguably useful for cross-lingual agents.

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?

There is no output schema, yet the description never says what a response looks like — whether it returns a last_id to feed back into `since`, message objects, or a count. For a cursor-based polling tool that omission is a real gap, though everything needed to make the call correctly is present.

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 code/limit/since are fully documented in the schema itself. The description's explanation of `since` (last received number, only later messages returned) merely restates the schema wording rather than adding format or edge-case detail, so the baseline of 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?

States a specific verb and resource ('대화방의 새 말을 읽는다') and narrows it to incremental new messages, which separates it from generic read siblings like read_feed/read_thread. It stops short of naming any sibling, so the differentiation is implied rather than explicit.

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 operating guidance: poll every few seconds to tens of seconds, and pass the last received number in `since`. There is no explicit 'do not use' case and no named alternative for reading full history, which keeps it from a 5.

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