create_draft

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

With no annotations, the description carries the full burden and does well: it discloses that the email is NOT sent and is only saved for user review, which is the critical safety-relevant behavior, and it reports the return payload ('full draft and its UID'). It omits permission/auth requirements and how invalid attachment paths are handled.

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 tightly written sentences; the core action, the non-send guarantee, and the follow-up routing are all front-loaded with zero filler.

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 7-parameter creation tool with no output schema, the description covers what an agent most needs: what is created, that nothing is sent, what is returned, and how to continue editing. Only auth/permission context and edge-case attachment handling are absent.

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 schema fully documents to/cc/bcc/subject/body/html/attachments. The description adds no parameter-level meaning (e.g. format expectations for the recipients array), so the 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?

States a specific verb and resource ('Create a new email draft') plus the destination ('Yahoo Mail Drafts folder'), which is unambiguous. It differentiates itself from update_draft explicitly, though it never distinguishes itself from the sibling create_reply_draft, so sibling differentiation is only partial.

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?

Names the follow-up alternative and the condition that selects it: 'To revise the draft later, call update_draft with that UID.' It also clarifies the non-sending workflow, telling the agent the user sends manually. It does not state when a draft is preferable to a reply draft or other creation paths.

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