auth_refresh

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that both tokens are rotated, which is a critical behavioral trait (old tokens become invalid). It also states that new tokens are stored in session config, making the side effect transparent. This is meaningful behavioral context beyond what the schema conveys.

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 sentences, zero filler. Each sentence carries meaning: what it does, what rotates, where tokens go, and when to use it. No redundant phrasing or wasted words.

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 single-parameter, no-output-schema tool, the description is fairly complete. It covers the purpose, the rotation behavior, the storage side effect, and the usage trigger. The only minor gap is a warning that the supplied refreshToken may be expired/invalid and what error behavior to expect, but overall this is well-covered for the tool's simplicity.

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% with a single optional parameter (refreshToken) that already has a description. The description adds marginal value by explaining rotation behavior, but the single parameter is well-documented in the schema. The baseline of 3 is elevated slightly because there's essentially nothing ambiguous to clarify with one optional param.

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 verb+resource ('Refresh an expired JWT access token using the refresh token') with specific scope (access token refresh), including the rotation behavior. It's clear what this tool does and distinct from auth_login/auth_register which create tokens from scratch. The purpose is 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 says 'Use when the current token has expired,' which provides clear context for when to invoke this tool. It doesn't explicitly name alternatives or exclusions, but the auth_* sibling cluster (auth_login, auth_register, auth_me) makes the use case reasonably distinct. Could be strengthened by noting to use auth_login if no refresh token exists.

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