gmail_create_draft

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds two useful behavioral facts beyond them: the action persists without sending, and the result lands in Drafts. It says nothing about auth requirements, recipient-optional behavior, or size handling for a 4 MB attachment limit.

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, the non-send constraint front-loaded in the first sentence where it matters most. Nothing is wasted and nothing is buried.

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 7-parameter create tool with no output schema, the description is thin but the schema carries parameter semantics and annotations carry the safety profile. It never clarifies the notable edge case that a draft can be created with no recipients, which an agent would benefit from knowing.

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 86%, so the schema already documents recipients, body/html relationship, and the attachment size cap. The description adds no parameter detail at all (e.g., that 'to' is optional for a draft), so the baseline 3 applies and no credit is earned.

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?

States a specific verb+resource ('Save a draft in Gmail') and, crucially, negates the sending behavior ('does not send'), which is the core distinction from the sibling gmail_send_draft. The verb/resource pair is unambiguous, though it never names a sibling explicitly.

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 parenthetical 'does not send' implies the usage context (use when you want to stage a message rather than deliver it), which is genuinely useful given gmail_send_email and gmail_send_draft exist as siblings. However, there is no explicit when-to-use, when-not, or named alternative, so guidance is only implied.

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