create-forward-draft

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

Annotations declare readOnlyHint false, destructiveHint true, and openWorldHint true, which already inform the agent about mutation and flexibility. The description adds the valuable clarification 'does not send' — a behavioral guarantee beyond the annotations. It does not contradict any annotation.

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 brief but redundant: the first sentence and the tip both repeat 'Create a forward draft.' The tip could be merged into a single sentence without losing meaning. It is not poorly structured, but it wastes a little space with repetition.

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 schema provides detailed parameter descriptions, including the requirement for messageId. However, the description does not mention that a forward requires an original message or that the body field structures the forward content. For a tool with nested objects and 5 parameters, the description relies heavily on the schema, which is mostly sufficient but lacks high-level context about the operation.

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 80%, so the schema already documents most parameters (messageId, confirm, etc.). The description adds no parameter-specific guidance. Per the rubric, with high schema coverage the baseline is 3, and there is no additional value here.

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 ('Create a forward draft') and immediately clarifies the critical distinction that it does not send. This differentiates it from siblings like send-mail, forward-mail-message, and create-reply-draft. The reader instantly knows what the tool does and why it exists.

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?

Provides a clear usage context: 'Useful when user wants to review before sending.' This tells the agent when to prefer this tool over a direct send. It does not explicitly name alternatives, but the hint implies the alternative (sending immediately) and the condition is unambiguous.

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