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

The description goes beyond annotations by disclosing the append semantic ('기록이 하나 더해진다'), which tells the agent that repeat calls accumulate records rather than updating — meaningful context reinforcing idempotentHint=false. It also surfaces the auth requirement (manageToken). It does not say what the response contains (e.g., the new record id).

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?

Three compact sentences with the core action and scope front-loaded, then the side effect, then the precondition. No filler; only '기록이 하나 더해진다' borders on restating the action, but it carries real semantic weight.

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 non-idempotent mutation with no output schema, the description covers the essential: what is captured, that a record accumulates, and that a manageToken is required. The only gap is the return value (record identifier or confirmation), which matters if the agent must chain calls.

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 100%, so all six parameters are already documented with examples. The description only restates the captured fields (date/method/recipient count) and adds no format, validation, or edge-case guidance beyond the schema; the optional 'note' and 'recipients' handling is left entirely to the schema.

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 (기록한다 / 소집통지) plus exactly which fields are captured: date, method, and recipient count, with the scope constraint '(모든 안건)'. It is clearly distinct from siblings like create_draft_meeting or close_meeting, though it does not name them 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 implied rather than stated: it records a notice once one has been sent, and it discloses the prerequisite 'manageToken 필요'. There is no explicit when-not condition or reference to an alternative tool, so an agent must infer the trigger from context.

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