create_draft_reply

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

With no annotations, the description carries the full burden. It transparently states that the tool creates a draft and does not send it, and it adds a useful generate-first workflow. However, it doesn't disclose whether the draft overwrites an existing one, whether it returns a draft identifier, or any auth/permission requirements.

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?

Two sentences, no filler. The core action is front-loaded, and the second sentence provides essential workflow guidance without unnecessary elaboration.

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 low-complexity tool with five simple parameters and full schema coverage, the description is mostly sufficient. It captures the main workflow and purpose. It could be stronger by explicitly contrasting with send_email, but the current wording already implies the difference.

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 100%, so the baseline is 3. The description reinforces that reply_body should be generated in conversation first, but it does not add meaningful semantic detail beyond the schema's per-parameter 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 states a specific verb and resource: 'Save a draft reply to an email in Gmail.' This clearly distinguishes it from its siblings, send_email and get_unread_emails, since it is about saving rather than sending or reading.

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 clear workflow guidance: generate the reply content in the conversation first, then use this tool to save it. It doesn't explicitly state when not to use it or mention alternatives, but the save-vs-send distinction is clear enough from the wording.

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