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

Adds rich context beyond annotations: confirms nothing is sent or scheduled, no subscriber is e-mailed, the status is always draft, and this server has no send tool. This goes well beyond the structured safety hints (readOnlyHint=false, destructiveHint=false).

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 'WRITE' and 'DRAFT' and is generally efficient, though the statement about no send tool slightly repeats the earlier manual-send instruction. Minor redundancy but not bloated.

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 simple create tool with no output schema and full schema coverage, the description covers purpose, constraints, non-actions, and body format. Nothing an agent needs to call it correctly is missing.

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%, so all six parameters are already documented. The description mentions body format (Markdown/HTML), but that duplicates the schema only; no additional parameter meaning is provided.

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 ('create a DRAFT email'), clarifies the resulting status ('always draft'), and distinguishes the operation from sending or scheduling. An agent can tell this apart from sibling tools like update_email_draft without opening the schema.

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?

Explicitly explains when not to expect sending or scheduling and directs the user to Buttondown for that action. However, it does not name the sibling update_email_draft for modifying an existing draft, leaving that routing to inference.

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