auth_refresh

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

Goes meaningfully beyond the annotations: it discloses that both tokens are rotated (so the old refresh token becomes unusable and retries with it will fail) and that new tokens land in session config rather than being surfaced. That rotation detail is the single most important non-obvious behavior for this call. It stops short of describing failure modes (expired/revoked refresh token → re-login required).

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 the action, then the side effect, then the storage location, then the trigger condition. No filler and no repetition of the tool name.

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 one-parameter auth tool with annotations covering the safety profile, this is nearly complete: action, rotation side effect, and storage destination are all covered. The only real gap is whether the new tokens are also returned in the response, which matters for an agent that needs to use them without relying on session state.

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% and the schema already explains that an omitted refreshToken falls back to STORNO_REFRESH_TOKEN. The description only says 'using the refresh token' and adds no format, precedence, or override semantics beyond what the schema states. Baseline 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 (refresh) and resource (expired JWT access token), plus the mechanism (refresh token). It is clearly distinct from auth_login and auth_me, though it never names those siblings explicitly, so the differentiation is implicit rather than stated.

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?

"Use when the current token has expired" gives a clear triggering condition, which is the main decision an agent faces here. It does not state the inverse case (e.g., when no refresh token exists, fall back to auth_login), so the alternative path is left to inference.

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