Save Draft

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

Annotations show readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds that the tool returns a server-assigned UID and that drafts can be incomplete. This provides useful behavioral context beyond annotations, though it doesn't detail all side effects (e.g., overwriting).

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 sentences conveying all key information (action, destination, optionality, return value). No unnecessary words. Front-loaded with the core purpose.

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 9 parameters and existing schema descriptions, the description covers the essential behavior (saving draft, optional fields, return UID). It does not explicitly explain threading (inReplyTo, references) or attachment handling, but those are documented in the schema. Completeness is adequate for the tool's complexity.

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 schema already documents most parameters. The description adds the note that 'All fields are optional', but this is already inferable from required:0 in the schema. The description does not compensate for undocumented parameters (the remaining ~11%).

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 action ('Save an email as a draft'), the target resource ('in the Drafts folder'), and the distinction from sending ('without sending it'). It also notes that all fields are optional, which differentiates it from send_email or other 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?

The description implicitly tells when to use (when you want to save a draft without sending). It lacks explicit 'when not to use' or comparisons to siblings like send_email, but the context of sibling tools and the phrase 'without sending it' provides sufficient guidance.

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