save_draft

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

With no annotations, the description carries full burden. It discloses the return value ({draft_id}), but does not mention other behaviors like authentication needs, error handling, whether it overwrites existing drafts, or how accounts are resolved. Adequate but minimal.

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 two sentences with no redundancy. Both sentences are essential: the first states the action, the second provides usage context and return value.

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?

Despite having an output schema and clear purpose, the description fails to document any of the 7 parameters. For a tool with 0% schema coverage, this leaves users guessing about parameter semantics, especially optional ones like account, cc, bcc, and html.

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 description coverage is 0%, meaning the description adds no meaning to any of the 7 parameters. The description does not explain what each parameter is for, types, or constraints beyond what the schema provides.

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 instead of sending') and the resource ('email as a draft'). It implicitly distinguishes from sibling tools like send_email and send_draft by contrasting with sending.

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 provides explicit guidance on when to use: 'when the LLM should let the human review before committing to send.' It does not explicitly list when not to use or alternatives, but the usage context is clear.

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