Add or remove labels (two-phase)

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

Annotations already indicate destructive and non-read-only behavior. The description adds valuable behavioral context by explaining that removing INBOX archives a message and that a confirmation token is required after preview. It does not contradict annotations, though it could mention more about the two-phase mechanism's return value.

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?

The description is three concise sentences, each earning its place: purpose, archive side effect, and confirmation workflow. It is front-loaded with the main action and contains 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?

The description covers the core purpose and key side effect, but the two-phase workflow is under-explained: it does not state that the first call returns a preview and token, or what the token is. Given no output schema and a destructive mutation tool, this is a meaningful gap for an agent to invoke it correctly.

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 description coverage is 0%, so the description must compensate. It maps roughly to add_label_ids/remove_label_ids, explains the confirm_token role, and highlights INBOX behavior, but it does not mention 'account' or 'message_ids' explicitly. The added semantics are helpful but not exhaustive given the low schema coverage.

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 action: 'Apply or remove labels on messages,' with the title clarifying 'two-phase.' It clearly differentiates from sibling tools like trash, send, or read by focusing on label modification and noting the archive side effect of removing INBOX.

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 gives clear usage context: it modifies labels, and it warns that removing INBOX archives a message. It also provides workflow guidance ('Preview first, then confirm with the token'), but it does not explicitly name alternatives or when not to use the tool, which keeps it from a 5.

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