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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds the two-phase protocol that no annotation conveys: the call is proposed rather than executed, returns status='confirmation_required' with action_id and plan_token, and requires confirm_action to commit. It also bounds the blast radius (sent mail unaffected).

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, front-loaded with the effect, then the scope bound, then the confirmation protocol. Every sentence contributes and no wording is redundant.

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?

There is no output schema, so the description rightly documents the return shape (status, action_id, plan_token) and the required follow-up call. For a one-parameter destructive mutation with annotations covering the safety profile, nothing an agent needs in order to call it correctly 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 single parameter draft_id has 0% schema description coverage, so the description carries the burden, yet it adds no meaning beyond the self-evident name (e.g. where the ID comes from or whether it accepts a draft object reference). With one obvious integer ID this is a minor gap rather than a blocking one.

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?

"Discard a saved draft" gives a specific verb plus resource and immediately clarifies scope ("half-written letter is gone; nothing already sent is affected"), so an agent can tell this targets unsent drafts only. It stops short of naming a sibling such as mail_delete_permanently or mail_delete_by_filter, so the read of the name space is left implicit.

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 routes the agent: this tool is never the terminal action, and the write only occurs after confirm_action. That is concrete when-to-use/when-to-follow-up guidance. It does not, however, state when a draft should be discarded versus permanently deleted or batch-deleted, which are the real sibling alternatives.

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