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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action is permanent, explicitly says messages are not deleted but only unlabeled, and requires user confirmation before invocation. This covers the key side effects and safety expectations an agent needs, going well beyond the annotation baseline.

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 with no filler. The core action is front-loaded, followed by a key behavioral caveat and a safety instruction. Every clause earns its place, and there is no redundant information.

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 destructive action with no annotations and no output schema, the description covers the core behavioral aspects: permanence, effect on messages, and user confirmation. It does not mention how to discover the labelId (e.g., via list_gmail_labels), but that gap is more a parameter-semantics issue than a completeness issue. Overall it is mostly complete for the tool's complexity.

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 50% (mailbox has a description, labelId does not). The tool description does not compensate for the undocumented labelId parameter; it does not explain what a label ID is, how to obtain it, or its format. The only parameter-related context comes from the schema, which is insufficient for the half that is missing.

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 'Permanently delete a Gmail label' with a specific verb and resource, clearly distinguishing it from sibling tools like create_gmail_label, rename_gmail_label, and list_gmail_labels. It also clarifies the scope (messages are not deleted, only unlabeled), which further separates it from message-deletion tools.

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 an explicit 'when to call' instruction: ask the user to confirm before calling, because the action is permanent. It does not explicitly name alternative tools or state when not to use it, but the message-unlabeling clarification implies a distinction from message deletion. This is clear, actionable context for an agent.

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