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

Annotations already indicate readOnlyHint=false, destructiveHint=true, and openWorldHint=true. The description adds valuable context: that the draft is staged without sending, that the shared workspace is visible/editable by other callers, and that the operation is safe because it doesn't send. It also clarifies the return includes draft_id. This goes beyond annotations without contradicting them.

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 the purpose front-loaded. The second sentence is longer but packed with essential context about shared workspace and safety. No filler or redundant information; every part earns its place.

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 the output schema exists (it returns the full draft), the description covers the key aspects: purpose, usage context, behavioral nuances, and parameter semantics. It lacks nothing an agent needs to correctly decide when to use this tool and what to expect.

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 100%, so each parameter already has a description. The tool description adds semantic value by grouping key parameters (to, cc, bcc, etc.) and explaining that in_reply_to/references are for threading. This provides contextual understanding beyond the schema's individual definitions.

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 verb 'composes' and the resource 'a draft in one inbox', and explicitly differentiates from the send tool by noting nothing leaves the account until the send endpoint is called. It also distinguishes from other sibling tools like patch or delete by focusing on creation without 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 explicitly states when to use this tool: to stage outbound mail for review, and mentions the alternative send tool by name (post_agentmail_inbox_draft_send). It also warns about the shared workspace, indicating caution for other callers. This gives clear guidance on selection.

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