Delete Saved Draft

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

The annotations already declare destructiveHint=true and idempotentHint=false, so the description isn't needed for the safety profile. It still adds real context the annotations cannot: the required scopes (mailbox.read, mailbox.drafts.write), that deletion completes asynchronously in the background, and that a draft mid-send cannot be deleted — a meaningful failure-mode disclosure.

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, zero filler, with the most important constraint (only when the user asks) front-loaded, followed by permissions and behavioral caveats in descending priority.

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 no explanation, and the description covers permissions, async completion, and the in-flight-send restriction. The only minor gap is the If-Match precondition, whose use-case context (conflict avoidance) is left to the schema's one-line note.

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 draftId, If-Match, and mailbox_id are already documented in the schema, and the description adds no further parameter guidance. Baseline 3 is appropriate: it neither contradicts nor enriches the schema.

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 names a specific verb and resource ('Delete a saved draft'), so an agent immediately knows the operation. It does not, however, distinguish this tool from the near-identical sibling 'mailbox_delete_draft' (or from batch deletion tools), so an agent facing duplicate names gets no disambiguation help.

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?

'Delete a saved draft only when the user asks' is an explicit gating condition, telling the agent not to delete autonomously. It does not name alternatives (e.g., update_draft, send_draft, batch_delete) or state what to do when the draft is scheduled, leaving that inference to the agent.

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