create_reply_draft

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

No annotations are provided, so the description carries the full load and does disclose the key behavioral trait: 'The email is NOT sent,' plus auto-populated recipients, 'Re:' subject, and threading headers, and a statement of what is returned. It omits where the draft lands and any auth/permission expectations, so it is good but not exhaustive.

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 sentences, front-loaded with the action and its side-effect status, then the return value, then the follow-up tool. Every sentence earns its place with no redundancy.

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 7-parameter mutation tool with no annotations and no output schema, the description covers the essentials: what is created, what is auto-filled, that nothing is sent, what is returned (draft plus UID), and how to continue with update_draft.

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 every parameter (uid, body, html, folder, replyAll, attachments, includeQuote) is already documented in the schema; baseline 3 applies. The description's mention of auto-filled recipients and threading headers adds marginal context but no syntax or format detail beyond 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?

The description states a specific verb and resource ('Create a reply ... save it as a draft') and scopes it to an existing email identified by UID. This implicitly but clearly distinguishes it from the sibling create_draft (new message) and update_draft (revision). An agent can pick the right tool 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?

It gives clear usage context and explicitly routes the agent onward: 'use update_draft with that UID to revise it.' It does not spell out when-not-to-use (e.g., when a brand-new message is wanted, use create_draft), but the alternative for the revision path is named with its condition.

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