imap_save_draft

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

With no annotations provided, the description must disclose behavioral traits. It clearly states that no email is sent, which is a key behavioral point, and mentions the inclusion of defaultBcc when configured. However, it does not mention other important behaviors such as whether the draft is created immediately, what happens on failure, or how the Drafts folder is auto-detected.

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 extremely concise, just two sentences, and front-loads the core purpose and the key distinction (no send) upfront. Every phrase adds value without redundancy.

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 that the tool has 14 parameters and no annotations, the description is relatively sparse. It relies heavily on referencing imap_send_email, which may be acceptable if that sibling is well-documented, but it does not explain the core workflow, return behavior, or error conditions. Since there is no output schema, understanding the tool's side effects (e.g., returning the draft ID) is left to the agent's intuition.

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 itself provides descriptions for all 14 parameters (100% coverage), so the description does not need to explain each one. However, the description only references that it 'takes the same fields as imap_send_email' and mentions defaultBcc, but does not add any extra semantic guidance beyond what the schema already provides. The 'folder' parameter's override behavior is not elaborated in the description, though the schema has a description.

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 explicitly states the action ('Save an email as a draft'), the destination ('Drafts folder'), and clarifies that it does not send. It also distinguishes itself from imap_send_email by referencing the shared fields and noting the save-only behavior.

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 conveys when to use this tool (when you want to save a draft without sending) and implicitly contrasts it with imap_send_email, which is the obvious alternative. However, it does not explicitly state when to choose one over the other, such as 'use this when the user intends to send later'.

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