save_draft

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

With no annotations, the description carries the whole burden and does disclose the most important trait: the draft is not sent and a human completes delivery. It does not say what permissions are needed, whether an existing draft is overwritten, or what identifier comes back, which leaves real gaps for a write operation.

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 short sentences, front-loaded with the action and immediately followed by the safety-relevant caveat. No filler and nothing buried.

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 5-parameter, 4-required mutation with no output schema and no annotations, the description covers purpose, non-sending behavior, and the dual-body requirement. The main remaining gap is the return value (e.g., a draft ID) and any permission requirements, though the tool is simple enough that the omission is minor.

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 every parameter is already documented in the schema. The description only reinforces that both html and text must be supplied; it adds nothing about comma-separated address formatting or subject constraints, so baseline 3 applies.

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?

Names a specific verb and resource ("Save an email as a draft") and pins the destination ("the account's Drafts folder"). The closest sibling, check_connection, is unrelated, so there is no ambiguity an agent could fall into.

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?

"It does not send: a human reviews and sends it" clearly tells the agent this is the draft path rather than a send path, which is the key usage decision. It stops short of explicitly naming an alternative tool or stating prerequisites, so it is strong context rather than a full when/when-not rule.

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