gmail_list_drafts

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

No annotations are provided, so the description carries the full burden, and it adds a real behavioral disclosure: results exclude attachment info because 'format: metadata, which never populates the MIME parts tree.' This explains a non-obvious implementation consequence. The only gap is unspecified pagination behavior, but for a non-destructive list tool this is a strong transparency effort.

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 with zero waste. The first states purpose and ordering; the second delivers the critical caveat and the routing to the sibling tool. Every sentence earns its place and the most decision-relevant information is front-loaded.

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 two-parameter list tool, the description covers the essential gotcha (no attachments), names the fallback, and the schema covers account and maxResults constraints. The main omission is whether the listing returns all drafts or only the first page up to maxResults. Still, nothing an agent needs to invoke it correctly in the common case is missing.

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 50%: the account parameter is well described in the schema, while maxResults has no semantic description. The tool description reinforces account scoping ('on one account') and adds that results are newest first, but it does not clarify maxResults semantics such as pagination or whether the cap represents a full page. With roughly half the parameters undocumented in both schema and description, a 3 is appropriate.

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?

States a specific verb + resource + scope: 'List Gmail drafts on one account, newest first.' The one-account scoping and ordering distinguish it from broader search tools and from gmail_get_draft, which the description explicitly contrasts. An agent can pick this tool confidently without inspecting the schema.

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?

Explicitly names the alternative and the condition selecting it: 'use gmail_get_draft on a specific draft to see its attachments.' This tells the agent exactly when not to use this tool (needs attachment info) and where to go instead. Nothing is left to inference.

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