Draft Reply

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

With no annotations, the description bears full burden. It discloses automatic behaviors (subject prefix, to, conversation linking) and that the draft can be reviewed or sent. But it omits potential side effects, authentication needs, or whether the original message is modified, leaving some behavioral gaps.

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 concise with no wasted words. It uses bullet points for automatic settings and clear sentences for usage. Every sentence adds value, fitting in two short paragraphs.

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 6 parameters, no output schema, and no annotations, the description covers main functionality and automatic behaviors. It mentions that only body is required, explains draft lifecycle (review/send). Minor omissions: doesn't mention max attachment size (in schema) or permissions. Overall sufficient for context.

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 100% (all 6 properties have descriptions). The description adds value by explaining automatic defaults (subject, To, Conversation) and the purpose of reply_all, but the schema already describes cc_fields and from_field adequately. Extra context is minor, so baseline 3.

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 it creates a draft reply to an existing message, specifying the action (draft reply) and the resource (existing message). It distinguishes from siblings like create_draft (blank draft) and send_message (sending), as the draft is a reply that auto-populates fields.

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 context: it says only body is required and hints at when to use reply_all. However, it lacks explicit guidelines on when not to use (e.g., for non-reply drafts use create_draft) or comparison with alternatives, leaving the agent to infer usage from context.

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