create_draft

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description's job is to add context, which it does: threading headers set, original message quoted, recipients defaulting to the original sender, and the draft id returned. It omits auth requirements and the 25MB attachment cap (the latter covered in schema), but the added behavioral detail is substantive.

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?

Three tight sentences, front-loaded with what is created and where, then conditional behavior, then return value. No filler sentences.

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 an 8-parameter tool with no output schema, the description covers the operation, the important conditional mode, and the return value, so an agent can call it correctly. Missing only permission/limit context that the schema partially supplies.

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?

With 75% schema coverage, the schema already documents most fields; the description still adds real meaning for replyToMessageId by explaining its threading and quoting side effects and the recipient defaulting rule. Other parameters (to, cc, bcc, body, htmlBody, attachments) are left entirely 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 ('Creates a draft') plus the target location (Naver Mail drafts folder with the Korean name), which is unambiguous. It does not name siblings such as send_message or update_draft, so the differentiation is left implicit rather than stated.

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 explains the conditional behavior when replyToMessageId is supplied, which implies a reply-draft use case, but never says when to prefer this over send_message/reply or when not to use it. Usage is inferable rather than explicit.

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