LMS 연결(로그인)

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

The tool discloses significant side effects: it opens a non-automated browser, saves the LMS session via DPAPI, preserves a dedicated Chrome profile with only LMS cookies, and terminates the dedicated Chrome after detecting the LMS home. It also warns the user not to close the window directly, which is consistent with the openWorldHint and idempotentHint annotations.

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 detailed and mostly efficient, but some phrasing is repetitive and awkward, such as '원문 보기용 프로필로 정리합니다' and the repeated warnings about not closing the window and not passing credentials. Still, every sentence contributes necessary operational or safety information.

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?

The description covers the full workflow, side effects, user actions, and the follow-up step via get_auth_status when wait_seconds is 0. It does not explicitly state the tool's return value or output, but since no output schema is provided and the expected follow-up is clear, the behavior is sufficiently complete for an agent.

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?

The single parameter wait_seconds is fully described in the schema, including its default value of 120, the allowed range, and the special meaning of 0 (open and return immediately). The description adds useful behavioral context about waiting for LMS detection and session saving.

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 that the tool opens a normal browser at LMS /my/ for user-initiated login, and it distinguishes this from sibling tools like open_lms_source and get_auth_status by describing manual authentication and session preservation. The action, resource, and intended login workflow are 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 gives explicit usage instructions: the user must perform integrated login via the third 'ID login' tab and select a passkey for second-factor authentication. It also warns not to pass credentials and explains the wait_seconds=0 case, directing the agent to call get_auth_status afterward.

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