create-shared-mailbox-draft

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

The description adds a critical behavioral guarantee beyond the annotations: a draft is created but no email is transmitted. The annotations already indicate this is a write operation, but the explicit 'Does NOT send' clarifies the main side-effect boundary an agent needs to know.

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 with no wasted words. The action is front-loaded, and the crucial caveat that it does not send immediately follows.

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 draft-creation tool, the description plus schema cover the required inputs and the key outcome. It could mention how to later send the draft or what the response contains, but with no output schema those are not essential for correct invocation.

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?

The schema already provides descriptions for 88% of parameters, including bodyType defaults and required fields. The description itself adds no parameter-level detail, so it does not need to compensate for schema coverage.

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 ('Create'), a specific resource ('DRAFT in a shared mailbox'), and explicitly distinguishes the action from sending ('Does NOT send'). This clearly separates it from sibling tools like send-shared-mailbox-mail and create-draft-email.

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 the right use case—composing a draft in a shared mailbox—but does not explicitly name alternatives or state when not to use it. An agent must infer that sending tools and personal-mailbox draft tools are different based on the name and the 'Does NOT send' caveat.

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