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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the bar is lower. The description nonetheless adds real value beyond them: it reassures that already-sent mail is untouched and explains the Gmail/Outlook mailbox restriction and its failure mode (deleting sent mail), which the annotations do not convey.

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 action, then the safety note, then the constraint. Every sentence earns its place with no padding.

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 values need not be explained, and the destructive nature plus the mailbox restriction are covered. What remains implicit is error behavior on a non-existent or already-sent draft id, though this is a minor gap for a simple two-parameter operation.

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 both parameters (id, mailbox) are already well documented in the schema, including the id pattern and its provenance. The description adds no additional parameter-level meaning, so the baseline of 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 (throw away/discard) and resource (draft), and clearly distinguishes itself from siblings like drafts_create, drafts_send, and drafts_update. An agent can tell immediately this is the deletion operation on drafts.

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?

Gives an explicit environmental constraint ('Gmail mailboxes only') with the reason, which is actionable context for selecting the tool. It does not, however, name an alternative tool or describe the conditions under which discarding is preferable to drafts_update or letting a draft send.

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