send_gmail_message

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It explains that replies are supported and that thread_id triggers a reply, and it describes the return value. However, it does not explicitly warn that sending is an irreversible side effect or mention authentication prerequisites beyond the user_google_email parameter, which is a meaningful gap for a send action.

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 well-organized with Args, Returns, and Examples sections. It is longer than necessary because it duplicates schema field descriptions, but the examples and threading explanations are valuable. The structure helps an agent parse the information efficiently, though it could be slightly more compact.

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 (10 parameters, reply/threading behavior), the description covers most aspects: new emails, replies, HTML/plain body, CC/BCC, threading, and return value. It lacks explicit error handling or authentication prerequisites, but the examples and detailed parameter semantics make it sufficient for correct invocation in most cases.

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 90% schema coverage, the baseline is 3, but the description adds significant value beyond the schema. It clarifies that thread_id converts the send into a reply, explains the role of in_reply_to and references for threading, and provides examples for HTML formatting and CC/BCC usage. This goes well beyond the raw schema 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 tool's purpose: 'Sends an email using the user's Gmail account' and explicitly supports both new emails and replies. This distinguishes it from sibling tools like draft_gmail_message (which creates drafts) and send_message (which targets chat spaces), making the resource and action 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 clearly indicates when to use the tool ('to send an email') and when to use reply-specific parameters (thread_id, in_reply_to, references). It does not explicitly name alternatives or exclude other tools, but the context is clear enough for an agent to select it for sending Gmail messages.

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