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

Annotations already declare the safety profile (readOnlyHint false, destructiveHint false, idempotentHint false). The description adds one genuinely useful behavioral fact — that saving is not send authorization — but omits any note on idempotency key semantics, side effects on existing drafts, or what happens to source-derived content, much of which is buried in the schema.

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?

Two tight sentences with the primary action front-loaded and zero filler. It is efficient, though the extreme brevity contributes to the completeness gaps elsewhere rather than purely earning its leanness.

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 annotations cover safety. But for a 12-parameter create tool with nested source/attachment semantics and partial schema coverage, the description is too thin to be fully complete — it never touches the composition parameters it accepts.

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 only 58% across 12 parameters, including nested objects and a source object, so the description needs to compensate and does not. It mentions no parameter at all — not source, attachments, recipients, subject, or idempotency_key — leaving the poorly covered params undocumented in both places.

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 states a specific action (save correspondence without sending) and implicitly distinguishes itself from send_message/send_draft by negating sending. It does not name the sibling tools or explicitly frame the create-vs-update distinction with update_draft, but the core purpose is unambiguous.

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?

"for later work or review in conversation" implies the drafting context, and "Saving is not send authorization" gives a useful caution about intent. However there is no explicit when-not guidance or routing to siblings like update_draft, send_draft, or reply_message.

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