Remove a label

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

Beyond the annotations (readOnlyHint false, destructiveHint false), the description discloses an important side effect: the expunge against the label mailbox. It also mentions the need for confirmation or dry_run, which is critical behavioral information not captured by annotations.

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 two sentences, front-loaded with the core action, followed by a concise warning. Every word contributes, with no redundant or filler content.

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?

Despite lacking an output schema, the description covers the key operational trait (expunge) and the required safety check. It could mention return values or error conditions, but the core usage context is sufficient given the simple operation and available sibling-tool context.

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 schema already describes 4 of 6 parameters (67%), and the description adds context about the purpose of 'dry_run' and 'confirmed' by mentioning preview and confirmation. This supplements the schema for the two undocumented parameters (uid and confirmed) implicitly, though not explicitly.

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 a specific action ('Take a label off a message') on a specific resource (a label on a message), and distinguishes it from related tools (e.g., apply_label, bulk_remove_label). The added detail that 'the message itself stays where it is' further clarifies that this is not a move or delete operation.

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 provides clear operational context, explicitly warning that the operation ends in an expunge and advising to 'confirm it or preview with dry_run=true first.' It does not explicitly compare to alternatives, but the sibling tool names imply the scope (single label) and the guidance on safety is valuable.

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