Create Saved Draft

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

Annotations only declare non-read-only, non-destructive, non-idempotent, open-world; the description adds the authorization scopes and the non-obvious fact that adopt creates are made safely retryable by reusing an Idempotency-Key. That idempotency nuance is valuable context beyond the idempotentHint=false flag and does not contradict it. It does not discuss behavior on duplicate adoption without a key, but the essential traits are 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?

Four compact sentences, front-loaded with the purpose, then permissions, then action modes, then the retain/concurrency rule. No filler, though the override and Idempotency-Key points are stated twice within the same description.

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 14-parameter nested create tool with an output schema, the description covers purpose, auth, action selection, override precedence, and retry semantics. Details like mailbox targeting, attachment limits, recipient caps, and custom-header restrictions are delegated to the fully described schema, which is acceptable.

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 100% and the schema itself already documents the source.action enum, the Idempotency-Key reuse rule, and the override behavior, so the description largely restates structured data. It does add the cross-field precedence idea at a glance, but little meaning beyond what the schema provides. Baseline 3 is appropriate.

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 opens with a concrete verb and resource plus a scoping distinction ('Save a message for review without sending it'), which separates it from send_draft/send_message. It stops short of naming those siblings explicitly, so an agent must infer the boundary from the 'without sending' phrase.

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 gives clear operating conditions: required scopes (mailbox.read, mailbox.drafts.write), the four source.action modes, the rule that explicit content overrides prepared defaults, and the Idempotency-Key retry discipline for adoption. It does not say when to prefer mailbox_update_draft or mailbox_control_draft_schedule instead, which is the remaining gap.

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