create_draft

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

With no annotations, the description carries the full burden. It states the tool creates a draft and returns fields, but does not disclose behavioral traits like auto-saving, overwrite behavior, or that drafts are stored. It meets a minimal threshold but could be more informative.

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 very concise, two sentences, and front-loaded with the core action. Every piece of information serves a clear purpose without 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?

Given the tool has 10 parameters and no output schema, the description could provide more context (e.g., how drafts are handled, relationship to send_draft). It covers the basics but lacks depth for a complex tool with many options.

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 50%, so the description should compensate for undocumented parameters. It only adds one hint about reply_to_message_id, leaving many parameters (e.g., to, subject, attachments) with no additional meaning beyond the schema. More parameter guidance would be beneficial.

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 tool creates a Gmail draft, with specific verb 'Create' and resource 'Gmail draft'. The return fields are listed, and the scope requirement is mentioned. This distinguishes it from sibling tools like send_draft or send_message.

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 usage guidance for replies ('For replies pass reply_to_message_id') and mentions the required scope. However, it does not explicitly compare to alternatives or state when not to use this tool.

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