imap_save_draft

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose one key behavioral trait, that the email is not sent, and notes that account defaultBcc is applied when configured. However, it does not explain connection/account prerequisites, whether repeated calls create duplicate drafts, what happens with the folder override, or what a successful call returns. The description is not misleading, but it leaves several operational behaviors to the agent's inference.

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 concise sentences and front-loads the primary action and no-send distinction. There is no filler. The second sentence is compact, but it references imap_send_email, which is not present in the sibling list, slightly reducing its standalone clarity. Overall it is efficient and well-structured.

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 a 14-parameter tool with no annotations and no output schema, the description is adequately scoped for selecting the tool but thin on invocation details. The schema covers parameter meanings, and the description covers the core purpose, but return values, connection/account prerequisites, and draft-folder fallback behavior are not addressed. This is a minimum-viable definition with clear gaps around operational context.

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?

The schema already describes all 14 parameters in detail, so the baseline is 3. The description only adds a cross-reference to imap_send_email and account defaultBcc behavior, but the defaultBcc behavior is already stated in the bcc parameter description. The description adds little semantic value beyond what the schema provides, though it does not conflict with it.

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 action and resource: 'Save an email as a draft in the Drafts folder'. It also explicitly says '(no send)', which distinguishes it from send-related siblings like imap_confirm_send or imap_preview_send_email. An agent can immediately tell what this tool does and what it does not do.

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 usage context: use this tool when you want to persist an email as a draft without sending it. The '(no send)' contrast with send tools is a clear contextual signal, though it does not explicitly name alternative tools or exclusion conditions. It is slightly less explicit than the best examples but still unambiguous.

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