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

Annotations declare readOnlyHint=false and destructiveHint=false, so it is a non-destructive write. The description adds the reply nuance and the requirement to obtain a reply_to_message_id, which is extra context. However, it does not describe side effects (e.g., that the draft is saved to the account and retrievable later) or any authentication requirements. Given the annotations already indicate mutation, the description adds moderate value but not a full behavioral picture.

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?

Two sentences with no filler. The main action ('without sending') is front-loaded, and the reply guidance is provided efficiently. Every word contributes to clarity.

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?

The tool has 8 parameters and no output schema. The description covers the core action and the tricky reply scenario, but it does not clarify whether html and plain_text can both be provided, the relationship between them, or how the draft is later sent (e.g., via email_send_draft). It also doesn't mention error conditions or the expectation that drafts are stored. For a draft-creation tool with this many parameters, more guidance would improve completeness, but the description is adequate for basic usage.

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 only 25% (account_id and reply_to_message_id have descriptions). The tool description adds context specifically for reply_to_message_id (provider-specific formats and how to obtain it), which is valuable. However, it does not explain the common parameters (to, cc, bcc, html, plain_text, subject) beyond what the schema provides. With low coverage, the description could compensate more, but it only partially does.

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 clearly states the verb 'Create' and the resource 'email draft', and explicitly notes 'without sending', which distinguishes it from email_send_draft and email_send. It also hints at the reply scenario, making the primary purpose unambiguous even without examining sibling tools.

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 provides specific guidance for the reply case ('If replying, first read the source email...'), which helps when to use this tool with a reply reference. It does not explicitly mention alternatives like email_update_draft or email_send_draft, but the 'without sending' clarification implicitly distinguishes it from send operations. This is useful context though not exhaustive.

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