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

Annotations already indicate a mutation (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds valuable behavioral context: on IMAP the draft ID changes and the new ID must be used for email_send_draft, and that reading the draft first is advised to preserve unspecified fields. This goes beyond annotations.

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 contains an awkward fragment: 'without sending.' which appears as an incomplete sentence with a double space before it. While the core message is short, the structure is unclear and could confuse an agent. The placement of 'without sending' after the IMAP note seems out of order.

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?

With 9 parameters, no output schema, and sparse annotations, the description should clarify the update semantics and expected result. It mentions the new draft ID on IMAP but does not describe the return object, how missing fields are handled, or the exact behavior for non-IMAP providers. It also omits guidance on which parameters are typically updated together. The description is incomplete for an agent to confidently call this tool.

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 33%, with only draft_id, account_id, and reply_to_message_id having descriptions. The tool description provides no additional meaning for the remaining six parameters (to, cc, bcc, html, subject, plain_text). It does not clarify whether the update is a full replacement or a merge, nor which fields are optional. The description fails to compensate for the low schema coverage.

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 'Update' and resource 'exact existing draft', distinguishing it from create/send/delete siblings. The qualifier 'exact existing' implies it targets a specific draft, but it does not explicitly contrast with email_create_draft or email_get_draft. The redundant 'without sending' adds no value but does not mislead.

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 includes a precondition: 'Resolve/read draft first when preserving recipients/content matters.' This is useful guidance for a partial-update scenario. However, it does not explicitly state when to use this tool versus alternatives like email_create_draft or email_send_draft, nor does it list exclusion criteria.

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