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

With no annotations supplied, the description carries the full burden. It does disclose two important behavioral facts: the refresh token is persisted to [vault:drive_oauth], and the token is never returned. However, it omits what the start phase actually returns (presumably an authorization URL), error/expiry behavior, and any permission or scope requirements.

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 short sentences, front-loaded with the action and its two modes, followed by the security-relevant storage and return behavior. 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?

For a two-phase OAuth tool with no annotations and no output schema, the description is missing key return-value information: an agent cannot tell from the text whether the start call yields a URL, a session id, or nothing. The token-handling note is valuable but does not fully cover what a caller needs to drive the flow.

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?

There is one optional parameter with 0% schema description coverage, so the description must compensate. It does give the parameter meaning ('one-time code' used to finish the flow), but it does not say the parameter is optional, what format the code takes, or where the caller obtains it.

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?

Names a specific verb and resource ('Google Drive connect') and clarifies the two-phase nature of the operation (start vs. finish with a one-time code). An agent can easily distinguish this from siblings like drive_list, drive_put, or drive_read, which are data operations, though the description does not explicitly contrast them.

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 implies the conditional flow: call without a code to start, call with a one-time code to finish. That is a usable when-to-use rule, but it does not state prerequisites (existing session, where the code originates) or what to do if a connect is already in progress.

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