create_reply_draft

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

The description discloses key behaviors: it creates a draft (not sending), supports attachments with explicit size limits, and explains the chunking behavior for larger files. It also mentions the API used, providing full transparency without relying on annotations.

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 succinct but packs essential details—purpose, API, attachment limits, and behavior—into two sentences. The schema is well-structured and follows a logical order, making it easy to parse.

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's complexity (7 parameters, attachment rules, and draft creation), the description and schema fully cover all necessary context. It clarifies the draft nature, attachment handling, and required messageId, leaving no critical gaps for an agent to invoke it correctly.

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?

All 7 parameters have clear, concise descriptions in the schema, covering CC/BCC, body, mailbox, replyAll, messageId, and attachments. The description adds extra context for attachments (paths, size handling), ensuring the agent understands each parameter's purpose and constraints.

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's primary function: creating an unsent draft reply to an existing email thread via the Microsoft Graph createReply API. It also specifies the endpoint and attachment limit, leaving no ambiguity about what the tool does.

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 implies usage by stating 'unsent draft reply,' which distinguishes it from sending a reply directly. However, it does not explicitly contrast with sibling tools like reply_to_email or create_email_draft, leaving the decision to the agent based on implicit context.

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