iris_create_draft

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

With no annotations provided, the description must carry the behavioral burden. It discloses that the message is NOT sent, that it goes to a user-defined folder (with default), and that the folder is created on first use. However, it does not mention any required authentication (e.g., that the user must have logged in via iris_login), potential side effects (e.g., overwriting existing drafts), or the exact return format. These gaps are meaningful for a tool that creates a draft.

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 and efficiently front-loads the critical fact that the message is staged and not sent. It avoids redundancy and directly states the key behavioral constraint. However, it could be slightly more structured (e.g., explicitly listing parameter hints) but overall it is concise and well-organized.

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 tool has 7 parameters (3 required) and no annotations, the description is not complete for an agent to call it correctly. It lacks explanations for most parameters, does not mention the output schema (though one exists), does not describe error conditions or authentication requirements, and does not clarify whether the folder creation is automatic. While the core behavior is clear, the operational details are missing.

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 has 0% description coverage, so the description is the primary source for parameter semantics. Only reply_to_message_id is explained (to draft a threaded reply). The other six parameters (to, cc, bcc, subject, body, html) are only listed with types and titles, with no explanation of format, defaults, or interdependencies. This provides minimal assistance to an agent in correctly constructing the arguments.

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 verb ('Compose a message into the staging mail folder') and resource (draft), and explicitly clarifies that the message is NOT sent, which distinguishes it from a send operation. It also mentions the default folder and the reply_to_message_id for threaded replies. This clearly differentiates it from siblings like iris_update_draft and iris_delete_draft.

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 clear context: use this to create a draft that a human will later send, not to send directly. It also hints at the reply_to_message_id for threaded replies. While it doesn't explicitly name alternative tools (e.g., 'use iris_update_draft for modifying existing drafts'), the create vs. update/delete distinction is obvious from the tool name and siblings. It provides enough guidance for an agent to know when to select it.

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