save_draft

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

With no annotations, the description carries the disclosure burden. It reveals a non-obvious behavior: the tool does not send the email itself; it only stores a draft that must be confirmed and sent manually. It does not mention permissions or response details, but the most important behavioral trait is explicit.

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 whole definition is one compact sentence with the main action front-loaded and the manual-send caveat clearly attached. Every clause adds useful information with 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 tool has an output schema and no annotations, so return values need not be described, but parameter semantics are only partially covered. The key behavior is clear, yet some edge-case clarity about required fields and sibling routing is missing. Adequate, but not fully complete.

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 provides 0% description coverage, so the prose must explain the parameter semantics. It clarifies that 'to' may be empty and 'cc' is optional, but it leaves 'subject' and 'body' unexplained and does not state that the 'to' key is still required even if the list is empty. This is only partial compensation for undocumented parameters.

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 and resource: save a draft into the Drafts folder. It also explicitly says sending happens manually after human confirmation, which clearly distinguishes this tool from send_email and schedule_send in the sibling list.

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?

It gives clear practical context: use this to prepare a draft for later manual sending, and recipients can be added later because 'to' may be an empty list. It doesn't explicitly name alternatives or say when not to use it, but the workflow guidance is sufficient for basic routing.

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