draft_create

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

No annotations are given, so the description carries the full burden. It candidly discloses that the tool does not send, that sending requires a separate explicit action with policy enforcement, and reveals the auto-derivation behavior for reply/forward (recipients and subject prefixes). This goes well beyond the schema and alerts the agent to the critical side-effect boundary.

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 well-structured and efficient: a clear one-line purpose, a note on the sending split, and bullet points for the three modes. The 'DOES NOT SEND' warning and the call to draft_send are front-loaded, ensuring the agent sees the most critical behavior first. No filler or redundancy.

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's complexity (12 params, all optional, output schema present), the description is remarkably complete. It covers the key behavioral nuances for all three modes, explicitly warns about the sending split and policy enforcement, and names the sending tool. The schema provides descriptions for many parameters, and the output schema handles return values, so no critical information is 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 description adds meaningful context beyond the schema: it explains how reply_to/forward_of drive mode selection, that subject is required for fresh drafts, and that forward drafts default to empty recipients. The schema already covers many parameters with descriptions, and the description complements rather than repeats. A minor gap is no mention of template parameters, but that is not central.

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 and resource: it creates a draft (fresh, reply, or forward) and immediately clarifies that it does NOT send. It explicitly names the sibling draft_send as the separate sending step, which distinguishes it from that tool. The three modes are clearly explained via reply_to and forward_of, making the tool's function unmistakable.

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 explicitly states when to use the tool (to create a draft) and when not to (do not send; call draft_send separately). It explains the intentional split and that sending is the only path where the outbound allowlist policy is enforced. It also details the mode selection logic based on reply_to/forward_of and names the alternative tool draft_send.

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