Draft a Gmail reply (not sent)

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

With no annotations provided, the description carries the full burden and does well by disclosing that the draft is visible in the Drafts folder, not actually sent, and requires Gmail authorization (referencing GMAIL_SETUP.md). It also explains how thread_id affects recipient/subject inference, adding useful behavioral context. A minor gap is that it doesn't describe what happens after the draft is created (e.g., return value), but this isn't critical.

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?

Three sentences, front-loaded with the most important fact (not sent), and each sentence adds distinct value. No repetition of schema content; it's tightly written and easy to parse.

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 5 parameters and no output schema, the description is adequately complete: it explains the two invocation modes, parameter relationships, and a prerequisite. The only omission is a explicit description of the return/confirmation behavior, but given the tool's simplicity and schema coverage, this is acceptable.

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 coverage is 100%, so the baseline is 3, but the description adds meaningful semantics: it explains that thread_id can come from search_gmail_for_job or scan_job_updates, clarifies that subject is ignored when thread_id is used, and explicitly states that 'to' is required when thread_id is omitted. Examples and precedence rules go beyond the schema descriptions.

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 specifies a clear action ('Create a real Gmail draft') and a distinct behavioral outcome ('does NOT send it'), distinguishing it from the sibling send_gmail_email. It also names the concrete resource (Drafts folder) and two usage modes (reply vs new message).

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 provides solid usage context: when to reply within a thread (pass thread_id with examples of source tools) and when to start a new message (pass to + subject). It also notes the authorization prerequisite. However, it doesn't explicitly name send_gmail_email as the alternative when sending is actually intended, though the 'does NOT send' phrasing implies it.

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