mail_create_draft

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

Annotations already cover the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=true), so the bar is lower. The description adds meaningful context: the message is unsent, delivery is a separate high-risk action, and it discloses the automation:Mail permission requirement.

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 compact sentences with zero waste; the core action and the delivery caveat are front-loaded, and the metadata tag is deferred to the end.

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?

An output schema exists, so return-value documentation is unnecessary, and permissions plus idempotency behavior are noted. Complete for invocation, though it says nothing about approval flow (the _approvalId param implies human approval) which a draft write could surface.

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 100%, so all five parameters (including _idempotencyKey and _approvalId) are already documented in the schema. The description adds no parameter-level meaning, which is the correct baseline when the schema does the heavy lifting.

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?

States a specific verb and resource ('Create an unsent outgoing message in Mail') plus the return value ('return its scripting ID'). The 'unsent' qualifier and 'Delivery is a separate high-risk action' cleanly separate it from the mail_send sibling.

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?

Explicitly signals that this tool composes but does not deliver, routing the agent away from send semantics. It does not name the alternative (mail_send) directly or state exclusion conditions, so a small inference remains.

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