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

Annotations already flag destructiveHint=true, but the description goes much further: it explains returns no body, irreversibility, shared-account side effects affecting other callers' drafts, and recommends a safe read-before-delete pattern. This is excellent behavioral disclosure beyond the structured hints.

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 sentences, each earning its place: what it does, return behavior, and critical caveats. The most important fact is front-loaded, and the safety advice is compactly appended without redundancy.

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?

For a destructive delete tool with no output schema, the description covers the essential operational concerns: deletion target, no response body, irreversibility, account-sharing risk, and a suggested read-before-delete safeguard. Nothing an agent needs to invoke it appropriately 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?

Schema description coverage is 100%, so all three parameters (inbox_id, draft_id, Authorization) are already documented. The description adds no parameter-specific syntax or relationships, which meets the baseline but doesn't improve on 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?

Description states a specific action ('Permanently deletes an unsent draft') with resource scope, clearly distinguishing this from message/thread deletes by emphasizing it only targets unsent drafts. The first sentence is unambiguous and the tool's destructive nature is explicit.

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?

Description gives clear usage context: it is for unsent drafts, cannot be undone, and should be preceded by reading with get_agentmail_inbox_draft if unsure. It does not explicitly enumerate sibling alternatives, but the 'read it first' guidance effectively tells the agent when to use the read tool rather than acting directly.

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