mail_prepare

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

Annotations only say it is a non-read-only, non-idempotent, open-world, non-destructive call. The description adds genuinely new behavior: it stages into the local outbox, returns a preview plus operation ID, never transmits, refuses to treat mailbox content as send authorization (prompt-injection defense), and enforces UIDVALIDITY/attachment-folder constraints. That is substantive context beyond the structured fields.

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, front-loaded with purpose and the send/no-send boundary before the constraint clauses. Dense and largely waste-free, though the telegraphic fragments ('Original-message actions require observed UIDVALIDITY') trade a little readability for brevity.

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?

With no output schema, the description usefully declares the return shape (full preview and operation ID). For a 12-parameter mutation tool the main remaining gap is the post-prepare lifecycle and body/addressing semantics, but safety and preconditions are covered.

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 0% across 12 parameters, so the description carries the burden and only partly discharges it. It clarifies kind (matching the enum), links uid/uidValidity to original-message actions, and constrains attachments, but to/cc/bcc, subject, text/html, folder, and accountId get no added meaning.

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) plus the resource and all four modes (new, reply, reply-all, forward), scoped to the local outbox. The clause 'does not send' cleanly separates it from mail_send_prepared and the draft-editing siblings without needing either 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?

'Does not send' establishes the boundary with mail_send_prepared, and two explicit prerequisites are given: original-message actions require observed UIDVALIDITY, and attachments must live in the approved uploads folder. It stops short of naming the sibling to use next or the exact call that observes UIDVALIDITY, so it is strong but not fully routing.

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