Send an email (two-phase)

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

The description discloses the critical two-phase behavior and the token rejection rule, which are not captured by annotations (destructiveHint, idempotentHint). This adds substantial context beyond the structured fields, explaining why a token is required and what happens if one is not received.

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 sentences, front-loaded with the main verb and resource. It wastes no words and clearly outlines the two-phase flow, including a critical safety warning.

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 tool with 8 parameters and a two-phase workflow, the description covers the essential flow (preview and token) and the constraint of reusing identical arguments. It does not describe the preview content or error cases, but with no output schema, the missing details are not critical for basic invocation.

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 only 13% (only confirm_token has a description). The description explains confirm_token's role well and implies that other parameters must remain identical between calls, but it does not elaborate on cc, bcc, account, or reply_to_message_id. These are self-explanatory by name, but the description does not fully compensate for the low coverage.

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 'Send mail from a connected account' with a clear verb and resource, and the title 'Send an email (two-phase)' adds the key nuance. It distinguishes from siblings like gmail_create_draft by focusing on direct sending, though it does not explicitly contrast with gmail_send_draft.

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 gives explicit two-phase usage: call without confirm_token for a preview, then with the token to send. It also warns against inventing a token. It does not mention when to use this tool vs alternatives like gmail_send_draft, so it lacks explicit exclusions, but the procedural guidance is strong.

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