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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation nature is covered. The description adds valuable context: it must only be used with user consent, and it supports multiple providers. It also hints at reply behavior via reply_to_message_id, which is beyond the 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 two sentences with no filler. It front-loads the core purpose (send/reply) and then adds the reply hint and consent requirement. Every word earns its place, and the structure is clean.

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 no output schema, the description is relatively sparse. It does not explain what happens on success or failure, how to handle multiple connected accounts (though account_id is in schema), or edge cases like invalid recipients. It covers the essential 'when' but lacks depth for a complex operation.

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?

Only 2 of 8 parameters (account_id and reply_to_message_id) have descriptions in the schema, which is 25% coverage. The tool description does not explain common parameters like to, cc, bcc, subject, html, or plain_text. It mentions reply_to_message_id but that is already covered in the schema, so it adds no new meaning. With low schema coverage, the description should compensate, but it does not.

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 tool sends or replies to an email from a connected Gmail, Outlook, or IMAP account. It distinguishes itself from sibling tools like email_create_draft and email_send_draft by emphasizing direct send/reply, and mentions the reply_to_message_id for true replies, which sets it apart from draft workflows.

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 provides clear context on when to use this tool (to send or reply) and includes a critical safety guideline about only sending after user approval. However, it does not explicitly exclude alternatives like email_create_draft or email_send_draft, so the differentiation is implicit rather than explicit.

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