Send one approved reply

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

The description discloses side effects: 'marks source read, threads send.' It explains default behaviors for quoteOriginal and appendSignature. However, it lacks details on irreversibility, immediate sending behavior, or auth requirements. Given no annotations, the description carries the full burden but misses some important behavioral traits.

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 concise at 5 sentences. It front-loads the purpose, then systematically explains key parameters and their defaults, and ends with a usage warning. Every sentence adds value without redundancy.

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 tool's complexity (12 parameters, 3 required, no output schema), the description is incomplete. It does not explain the return value, error conditions, or behavior for all parameters. Important fields like 'to' and 'subject' are left undiscussed, and the overall sending mechanism (e.g., synchronous, queued) is not addressed.

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?

With 0% schema description coverage, the description compensates partially by explaining 6 of 12 parameters (messageId, body, format, html, quoteOriginal, appendSignature). Critically, it omits descriptions for required parameters 'to' and 'subject', as well as 'cc', 'bcc', 'accountAlias', and 'chatScope'. This leaves significant gaps for correct invocation.

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 'Send one approved reply' and specifies the required messageId. It distinguishes from the sibling tool 'send_new' by explicitly stating 'For new outbound / campaigns use send_new instead.' The verb and resource are specific, and the scope (replying) is unambiguous.

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 advises using 'send_new' for new outbound emails, providing a clear alternative. It also warns 'Never run without explicit approval.' However, it does not address when to use this tool versus multi-account variants (e.g., multi_gmail_send), which are present in the sibling list.

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