Create a draft

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

Annotations already declare a non-destructive write (readOnlyHint=false, destructiveHint=false), and the description usefully reinforces that nothing is transmitted to recipients. It says nothing about what the call returns (a draft id?), whether repeated calls duplicate drafts, or how the saved draft is later sent via send_draft — a notable gap given there is no output 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 short sentences, with the action and its key constraint front-loaded and the routing hint second. No filler or restatement of the title.

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 nine-parameter compose tool with no output schema and no annotation coverage of results, the description leaves the agent unsure what comes back and how to follow up. The sending-suppression fact is covered, but the draft lifecycle is not.

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% and all nine parameters carry inline descriptions, including conditional optionality (to/subject optional when replying, reply_all semantics). The description adds no parameter-level detail beyond that, so the schema does all the work and baseline 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 concrete verb and resource ("Save a message ... in Gmail Drafts") and immediately negates the confusable action ("without sending it"), which separates it from send_email and send_draft. It stops short of naming those siblings explicitly, so differentiation relies on inference.

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?

"The safe default for writing" gives the agent a clear selection rule for the compose-without-transmitting case, and "new or reply" covers both entry points. It offers no explicit exclusion or pointer to send_email/send_draft for the opposite case, so it is clear context rather than full when/when-not guidance.

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