save_draft

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

Annotations already mark the tool as non-readonly and non-destructive, so the bar is lower. The description adds useful lifecycle context—'compose over time' and how drafts are later sent or listed—without contradicting annotations. It doesn't mention side effects like overwriting, but the added workflow detail is valuable.

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 three sentences with a clear front-loaded purpose, followed by workflow and viewing guidance. No filler or redundancy; every sentence contributes to tool understanding.

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 8 parameters and no output schema, the description provides the essential workflow context (save, send, view drafts) that an agent needs. It doesn't explain return values, but the lifecycle and intent are sufficiently covered for a draft-saving tool.

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 input schema has 100% parameter description coverage, so the schema carries the burden. The description doesn't introduce new parameter details, but it implies the draft workflow (e.g., saving without sending), which is consistent with the schema's note that 'to' can be empty for drafts. Baseline 3 is appropriate.

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 action and resource: 'Save an email draft to the Drafts folder.' It distinguishes from sibling tools by explicitly referencing send_draft for sending and list_emails for viewing drafts, making the purpose unambiguous.

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 clear when-to-use guidance: 'Compose over time, then use send_draft to send it.' It also names the alternative for viewing drafts ('Use list_emails with the Drafts mailbox'), offering explicit contextual direction beyond just stating the action.

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