Reply as a draft

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

With annotations offering no safety profile (all false), the description carries the burden. It discloses that the operation creates a draft (not a send), that the server sets the reply headers and quote, and that recipients depend on reply_all. It does not mention permission requirements or idempotency, but the core behavior is clearly and fully described.

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 with zero filler. The first sentence front-loads the key action and server behavior, the second gives the usage trigger with useful language examples, and the third delivers the essential negative constraint ('Nothing is sent'). Each sentence earns its place.

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 9-parameter tool, the schema covers most parameter semantics. The description supplies the high-level operation, the server-side behavior, and the intended trigger. It does not need to explain return values (no output schema) and adequately complements the structured schema, though it could mention permission requirements.

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 89%, so the baseline is 3. The description adds value by explaining the effect of reply_all ('recipients (sender, or everyone with reply_all)') and that the quoted original is automatically set, which clarifies the text and quote parameters. These details go beyond the schema's descriptions.

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: 'Saves a reply to a specific message into Drafts, in the same thread.' It also enumerates the server-set fields (In-Reply-To/References, Re: subject, recipients, quoted original) and explicitly says 'Nothing is sent,' clearly distinguishing it from reply_send and other sending tools.

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 provides an explicit trigger: 'Use this whenever the owner says "reply / answer / write a draft"' with language examples. It does not explicitly name alternatives like reply_send or create_draft for the 'when not' case, but the phrase 'Nothing is sent' and 'into Drafts' imply when not to use it.

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