create_reply_draft

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

With no annotations supplied, the description carries the full behavioral burden, and it does disclose the most important trait: the draft is not sent. It says nothing about whether the draft lands in a Drafts folder, whether reply_all changes recipient handling, what account defaults to when omitted, or what permissions are required.

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 short sentences, zero filler, with the core action and its non-sending nature front-loaded before the parameter note. Every clause carries information.

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 four-parameter draft-creation tool with no output schema and no annotations, the description covers the essential action and the non-send guarantee. It falls short on the reply_all semantics and on default account behavior, which an agent needs to call this correctly without guessing.

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 0%, so the description must supply parameter meaning, and it only clarifies one of four: 'account is an email or alias'. The semantically loaded 'reply_all' flag is left completely unexplained (all recipients vs. sender only), and message_id/body get no elaboration.

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 uses a specific verb+resource ('Create a threaded reply draft to a message') and clarifies the key distinction from a send operation with '(does not send)'. It implicitly separates this from siblings like create_draft, reply_to_email, and send_draft, though it does not name any of them explicitly.

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 parenthetical '(does not send)' implies the tool is for staging a reply rather than delivering it, which hints at when to use it over reply_to_email or send_draft. However, there is no explicit statement of when to choose this versus create_draft, nor any prerequisite or exclusion guidance.

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