send

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is known. The description adds valuable context beyond annotations: the requirement that a human approved the draft via gmail-approve CLI, which implies a safety gate and irreversible dispatch. It does not contradict annotations.

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 a single, well-structured sentence that delivers the core purpose and key precondition without wasted words. The parenthetical '(unconfigured)' adds brief status context without bloating the definition.

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?

With two required parameters and no schema coverage, the description is not sufficient for an agent to call the tool correctly. It does not explain what 'unconfigured' means operationally, how to find an approval_id, or what account values are valid. The absence of an output schema further increases the need for explanatory context, which is missing.

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%, so the description must compensate for explaining the two required parameters, account and approval_id. The description hints that approval_id is tied to the gmail-approve CLI, but it does not explain what account refers to or how either param should be formatted or obtained. This is minimal compensation for a 0% coverage situation.

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 ('Send') with a resource ('a draft') and a clear qualifying condition ('that a human already approved via the gmail-approve CLI'). This distinguishes it from siblings like stage_send, create_draft, and update_draft by emphasizing the final dispatch action after human approval.

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 clearly indicates this tool is for sending drafts that have already received human approval, giving a strong contextual cue about the intended workflow stage. However, it does not explicitly name alternatives or state when not to use the tool, though the approval condition implies it should not be used before approval.

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