gmail_send_draft

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the 'Cannot be undone' warning reinforces rather than adds beyond structured data. The description contributes some workflow context—'an agent drafts, a person sends'—but no additional side-effect detail beyond the annotation and schema.

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 short sentences, front-loaded with the key action, then the workflow separation, then the irreversible warning. No filler or repeated detail beyond what is useful.

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 simple two-parameter send action, the description and schema together give the agent enough to select and call it: required draftId, confirm flag with warning, and the destructive nature. It does not describe the return value, but no output schema exists and the operation is unambiguously 'send,' so the gap is acceptable.

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 covers confirm well with default, description, and warning, but draftId has no description in schema. The tool description's 'draft that already exists' supplies minimal semantic context for draftId. With 50% schema description coverage, the description adds only slight meaning beyond the schema.

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 uses a specific verb and resource: 'Send a draft that already exists.' It also explicitly separates this from creating a draft, which clearly differentiates it from draft-creation tools and removes ambiguous about the operation.

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 gives clear conceptual guidance by stating this tool is for sending an existing draft versus creating one, implying the creation tool should be used for authoring. It does not name a specific sibling tool, but the boundary is explicit enough for an agent to route correctly.

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