save_draft

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

Annotations only say this is a non-read-only, non-destructive, non-idempotent, open-world call. The description adds genuinely new behavior: the required 'draft' permission (distinct from append/send), the fixed Draft flag with no arbitrary target or flags, and the recipient allowlist constraint. It does not cover failure modes or what happens if a draft already exists, which is why this is not a 5.

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 short sentences with the core action and destination front-loaded, then permission and allowlist constraints. No filler, though the final clause about fixed flags is slightly terse and could be folded in more smoothly.

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?

With annotations covering the safety profile and an output schema covering return values, the description's job is to supply permission, targeting, and allowlist context, which it does. The remaining gap is idempotency/overwrite behavior, relevant since idempotentHint is false and drafts could collide.

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 the schema already documents all ten parameters, including the recipient allowlist note. The description's only parameter-level addition ('recipients may be omitted; supplied recipients obey the recipient allowlist') largely duplicates the schema's own recipients description, so baseline 3 applies.

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 ('Compose and save an unsent draft') plus the destination ('configured drafts mailbox or unique special-use Drafts mailbox'). The word 'unsent' cleanly separates it from the send_email sibling without requiring the schema to be opened.

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?

'Requires draft permission, not append or send' gives an explicit precondition for choosing this tool over send_email, and 'Recipients may be omitted' tells the agent the call is valid without addressing anyone. It stops short of naming an alternative tool or an explicit when-not-to-use rule, so it is clear context rather than full routing guidance.

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