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

Annotations provide readOnlyHint=false and idempotentHint=false, signaling a state-changing, non-idempotent operation. The description adds meaningful context beyond this: calling without mcp_session_id creates a new MCP session, the tool returns loginUrl and mcpSessionId, and the original auth call must be retried with the session ID. No contradiction with 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?

Purpose and trigger condition are front-loaded, followed by a numbered 4-step procedure. The length is justified by the interactive nature of the auth flow; every sentence contributes meaning and there is no filler.

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 correctly carries the burden of explaining return values — it names loginUrl and mcpSessionId and specifies exactly how each must be used in the full invoke→show→wait→retry loop. Minor gaps like timeout or error behavior don't prevent correct invocation.

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% — both provider (with per-provider data examples) and mcp_session_id are documented in the schema. The description adds the critical behavioral role of mcp_session_id in the retry flow, which the schema alone does not convey, justifying a score above the baseline.

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: it generates browser login URLs for designated SSU Campus providers (SAINT, LMS, LIBRARY). This clearly differentiates it from siblings like get_auth_status (status check) and logout_provider (session termination), so an agent can distinguish them without inspecting schemas.

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 trigger condition is explicit: '인증 도구가 AUTH_REQUIRED를 반환할 때 이 도구를 사용하세요' (use when the auth tool returns AUTH_REQUIRED), followed by a detailed 4-step procedure including a specific prohibition on substituting the loginUrl with other markdown links. It lacks explicitly named alternative tools, but the invocation context is clear.

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