create_draft

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

With no annotations, the description carries the full burden, and it does substantial work: it discloses that the tool stages rather than sends, that attachments are interpreted as local file paths, that the draft resource is returned, and that sending is deliberately excluded as a workflow constraint. It does not cover auth/permission needs or rate limits, but the critical behavioral boundary (no sending) is clearly stated.

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?

Roughly 50 words across three sentences, with the core action front-loaded in the first sentence, attachments semantics in the second, and the send-limitation workflow in the third. Every sentence adds distinct information; there is no fluff or repetition.

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?

Given no annotations, 0% schema parameter coverage, and an output schema that already covers the return value, the description covers the essential invocation knowledge: the operation's scope, the non-send constraint, and the local-path semantics of attachments. Minor gaps remain around address/message-id formats and prerequisites, but nothing blocks correct invocation for a straightforward draft creation.

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 0%, so the description must compensate. It does clarify the one genuinely ambiguous parameter — 'attachments are local file paths' — and frames the rest as email-draft fields (to, subject, body, cc, in_reply_to) which are largely self-evident. However, it leaves in_reply_to's expected format (e.g., message-id) and cc/address format unspecified, so compensation is partial.

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 uses a specific verb+resource pair ('Stage a draft') and immediately disambiguates from sending with 'Does NOT send.' None of the sibling tools create or stage drafts, so an agent can distinguish this tool without opening the schema. The intentional non-send scoping makes the purpose unmistakable.

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 description gives clear context that this tool is for staging drafts and explicitly excludes sending ('Sending is intentionally unavailable here'), routing the agent to the CLI for the send step. It lacks an explicit statement of when to use this tool over a sibling, but no sibling is a draft/send tool, so the exclusion plus named alternative (CLI) covers the key decision.

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