Save a new draft

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

Annotations declare non-read-only, non-destructive, non-idempotent; the description earns its keep by explaining the consequence — "Each call appends one new draft and never edits or deletes another" — which is exactly the append-duplication behavior idempotentHint=false implies but doesn't spell out. It also discloses hard quotas (20 attachments, 7 MiB, 10 MiB send limit), the From-address allowlist constraint, and the specific refusal conditions.

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?

The purpose and the never-sends guarantee are front-loaded correctly, but the compose_reply routing is split across two paragraphs that restate the same precondition, and the attachment limits are stated twice (inline and again in the refusal list). Dense and informative, but it could be trimmed by roughly a third without losing guidance.

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?

With annotations, a full output schema, and 100% parameter documentation already available, the description supplies exactly the missing layer: the reply-vs-new-vs-forward decision, attachment sourcing and limits, and the failure modes. Nothing an agent needs to invoke it correctly is absent.

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 coverage is already 100%, so the baseline is 3; the description goes beyond it by explaining cross-field semantics the schema states only per-field — in_reply_to additionally sets References, and attachments_from pairs with attachment_indexes as numbered by list_attachments. It stops short of explaining the cc/array normalization or the interaction of attachments with attachments_from in one call.

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?

"Save a new unsent draft in Drafts and return its Message-ID; this never sends" states a specific verb, resource, return value, and a critical scope boundary in one sentence. It is unambiguously distinct from compose_reply and forward_message, both of which it names.

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?

It gives explicit routing logic: if compose_reply is listed and the user wants to reply or compose, call compose_reply first; then call this after the composer fields were shown and agreed, or save from the composer view; otherwise call directly. It also names forward_message for the forwarding case, so the when/when-not/alternative triad is fully covered.

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