iris_create_draft

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

No annotations are provided, so the description carries the full burden. It discloses that the draft is not sent, that a human must send it, that folders are created on first use, and that passing '' or 'Drafts' targets the normal Drafts folder. It does not cover authentication or rate limits, but for a draft-creation tool these are less critical. The key side-effect (not sending) is prominently disclosed.

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 concise paragraphs. The first sentence states the core purpose and the not-sent caveat. The second paragraph focuses on the two parameters that need explanation (folder and reply_to_message_id). No fluff, every sentence earns its place, and the most important information (not sent) is front-loaded.

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 an 8-parameter tool with no annotations and an output schema present, the description covers the essential aspects: purpose, non-sending, folder behavior, and reply threading. It does not explain the html parameter's meaning (HTML vs plain text), which could be relevant, but the output schema may cover return values. Overall it is sufficient for an agent to use correctly.

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 0%, so the description must compensate. It explains folder (selection by display name, creation on first use, default, special values) and reply_to_message_id (threaded reply) in detail. It does not elaborate on cc, bcc, or html, but these are conventional email fields; to, subject, body are self-explanatory. Given the low coverage, the description adds meaningful semantics for the non-obvious 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 clearly states the action (compose a message into a mail folder as an unsent draft) and explicitly distinguishes it from sending by noting it is NOT sent. It also differentiates from sibling tools by focusing on creation rather than update/delete. The verb+resource combination is specific and unambiguous.

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 provides clear usage context for the folder parameter (including default behavior and special values) and for reply_to_message_id (threaded replies). It also implies when not to use this tool (if the intent is to send). However, it does not explicitly name alternative tools like iris_update_draft or iris_send (if it existed), so the guidance is good but not exhaustive.

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