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 nothing is sent, that the draft waits in the owner's outbox for the owner to read/edit/send, and that the call returns a link. That is meaningful non-obvious behavior; only auth/permission requirements are left unaddressed.

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?

Four short sentences, each earning its place, with the critical 'NOT sent' constraint and the 'give the owner the link' instruction front-loaded. No 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 tool with full schema coverage but no annotations and no output schema, the description covers the key unknowns: send semantics, the outbox handoff, and the returned link. It is complete enough to invoke correctly, though it omits any auth or connection prerequisites.

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 already documents all seven parameters. The description only reinforces plain-text body and the reply_to_uid reply mode, adding little beyond what the schema states; baseline 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 (prepare/draft) and resource (e-mail), and immediately distinguishes itself from mail_send with 'It is NOT sent'. An agent can tell this apart from mail_send and mail_read without opening a 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?

Explains the two modes (new e-mail, or a reply via reply_to_uid) and clarifies the draft-and-defer workflow. It does not explicitly name mail_send as the alternative for actually sending, but the 'NOT sent' framing implies the split clearly enough.

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