draft

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

It adds useful policy information ('Always allowed') and clarifies a key behavioral quirk: how the `in_reply_to` parameter handles threading and defaults to the original sender, which is behavioral context beyond the schema.

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 highly concise, utilizing only two sentences to capture the core functionality, the policy, and the complexity of reply threading. Every word contributes to clarity.

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?

Given the rich schema and annotations, the description completes the picture by explaining the operational context of drafting, especially regarding how reply threads are established and the default behavior of the tool.

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?

Although schema coverage is 100%, the description adds semantic value by explaining formatting (Markdown vs HTML rendering) and crucial usage details for parameters like `to` (recipient format and empty list default) and `subject` (automatic prefix when replying).

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 the primary function as saving a message to the Drafts folder. It differentiates this action (draft creation) from immediate actions like sending, implicitly setting it apart from the send sibling.

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 defines the use case (saving for later review) which is the primary differentiator from sending, but it does not explicitly state when *not* to use it or compare its usage requirements against alternatives like `send`.

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