create_draft

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that the message is saved to Drafts and never sent, but it does not mention permissions/auth needs, return behavior, or what happens on invalid recipients.

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?

Front-loads the key purpose and non-sending behavior, then uses a compact Args list for parameters. There is no wasted text.

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 and no output schema, the description is mostly complete for calling the tool: it explains the action, non-send guarantee, storage location, and all parameters. It could be stronger with auth/error or return details, but the core invocation needs are covered.

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, and it does document all five parameters: to, subject, body, optional cc, and html. It adds useful semantics such as body being plain text by default and html=True making it HTML, though array/string details are left to 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?

States a specific verb and resource (compose a brand-new draft email) and explicitly excludes replies, which distinguishes it from the sibling create_reply_draft. It also clarifies that the draft is saved, not sent.

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?

Gives clear usage context: brand-new email, not a reply, saved to Drafts and not sent. The alternative create_reply_draft is strongly implied by 'NOT a reply,' though not explicitly named as the tool to use instead.

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