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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context: it can be called without a key and is intended for frequent polling. This goes beyond the annotations without contradicting them.

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 a single, front-loaded sentence in Korean with an English parenthetical, covering purpose, usage, and auth in a compact form. No wasted words; structure is efficient.

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 read-only polling tool, it covers the essential usage: what it reads, how to use `since`, polling frequency, and auth requirement. It doesn't mention return format or `limit` behavior, but with no output schema and simple integer params, this is adequate.

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 only 33% (only `code` is described). The description compensates for `since` by explaining it as 'last_id' and how to use it, but `limit` remains undocumented in both schema and description. It partially fills the gap but not fully.

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 tool reads new messages from a chat room ('대화방의 새 말을 읽는다') with a specific verb and resource. It distinguishes itself from siblings like room_send and read_thread by emphasizing incremental reading after a `since` marker, making its purpose 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 gives explicit guidance on how to use `since` for incremental reads and recommends polling intervals ('몇 초~수십 초 간격으로 부르면 된다'), plus notes that no key is required. It does not explicitly list alternatives or when not to use it, but the context is sufficient for a read tool.

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