reauthorize

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

There are no annotations, so the description carries the full burden. It does disclose the important behavioural traits — a browser window opens automatically, the user must complete an interactive login, and a new token is persisted afterwards. It doesn't say whether existing credentials are replaced, what happens if the user closes the browser, or whether the call blocks until completion.

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 lines, front-loaded with what happens and then when to use it. Line one and line two overlap slightly on the browser-opening point, but 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?

An output schema exists, so return values need no explanation. Given an interactive, side-effecting, zero-parameter flow, the description covers the trigger, the user-visible behaviour, and the result; only failure modes (aborted login, blocked popup) are unmentioned.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool 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 and resource: re-login to Google in a browser to obtain a fresh token. That is clearly distinct from what a status-check sibling like auth_status would do, even though no sibling is named.

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?

Gives an explicit trigger: run it on authentication errors such as 401 or when the refresh token has expired. It does not name an alternative (e.g., checking auth_status first) or state when not to run it, so it stops just short of a 5.

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