create_draft

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

With no annotations provided, the description carries the full behavioral burden. It discloses the most critical behavioral trait: this tool does not send, only saves a draft. It also mentions local file attachment support. However, it doesn't detail other behaviors such as whether a draft confirmation is returned or how drafts are stored, but the key non-sending distinction from send_message is covered.

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?

Three short sentences, each with a distinct purpose: the main action, the non-sending clarification, and the attachment capability. It is front-loaded with the primary function and contains no filler words.

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 7-parameter tool with no output schema and no annotations, the description covers the most important behavioral caveat (no sending) and the basic draft workflow. It does not explain return values, but that isn't required without an output schema. cc/bcc and html/body alternatives are left to the schema, which documents them adequately. Overall, it is complete for the core use case.

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 coverage is 71%, so the schema documents most parameters. The description adds minimal parameter-specific information beyond the schema—it only mentions 'local file attachments', which the schema already covers. cc and bcc lack descriptions in both the schema and the description, so there is no compensation for those gaps. Overall, the description adds little value for parameter understanding.

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?

Description uses a specific verb ('Compose'), names the resource ('new email'), and the action ('save it to Drafts'). The explicit 'Does NOT send' distinguishes it from send_message, and 'new email' distinguishes it from reply/forward tools. This gives clear differentiation from siblings.

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 clearly states that after using this tool, the user reviews and sends the email manually in Proton, implying this tool is for draft creation rather than sending. It explicitly negates sending, which tells an agent when NOT to use it, but it doesn't name alternative tools like send_message. The workflow guidance is clear but not fully explicit about sibling selection.

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