create_email_draft

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states 'Create an email draft' with no mention of whether this is a read/transient operation (creating a draft is non-destructive but the agent needs to know it doesn't send), whether scheduling/rate limits apply, or what happens with the 'account' selection fallback. Critical behavior — that this creates a draft and does NOT send it — is only implied by the name 'draft' and not 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?

The description is extremely concise — a single sentence with zero wasted words. It is efficiently front-loaded and easy to parse. However, the brevity is a double-edged sword: while there's no fluff, important differentiating context is missing. For conciseness alone, this is well-executed.

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 the crowded sibling space (draft_email, draft_reply, draft_follow_up, send_email all nearby), the description is incomplete. There is no output schema description detail, no distinction from siblings, no behavioral note that this does not send the email. For a draft-creation tool operating in a workspace with many overlapping email/delegation/commitment tools, one sentence is insufficient.

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 coverage is 100%, so all 5 parameters are documented in the schema. The description adds no parameter information beyond the schema. According to the baseline, 100% coverage earns a 3. The description doesn't compensate with format/semantic details (like whether 'to' supports multiple formats or what 'first available' means for account selection), but the schema already carries the load.

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 states a clear verb+resource ('Create an email draft'), which provides basic purpose clarity. However, it doesn't distinguish this from sibling tools like 'draft_email', 'draft_reply', 'draft_follow_up', or 'send_email' — the agent would struggle to know which draft/send tool to pick. The single sentence explains the action but not the scope or differentiation from nearly identical siblings.

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?

There is no guidance on when to use this tool vs. alternatives. Siblings include 'draft_email', 'draft_reply', 'draft_follow_up', and 'send_email' which all overlap significantly in purpose. The description gives zero context about when to choose create_email_draft over draft_email, or when a reply/follow-up variant would be more appropriate. This is a significant gap given the crowded sibling space.

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