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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=true; the description adds useful context that the message lands in a DRAFT folder and is human-reviewable. It does not say whether saving overwrites an existing draft, whether the call fails without a valid mailbox id, or what the response contains (draft id), which matters for later manipulation.

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?

A single front-loaded sentence with the write marker first and the DRAFT/send contrast immediately after; the parentheticals carry real information rather than filler. Dense but not bloated.

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 write tool with no output schema and full annotation coverage, the description covers the core behavior and mailbox-identifier alternatives. Gaps remain on return values (no draft id) and on idempotency/overwrite behavior, which an agent would need to chain a follow-up send or edit.

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?

With 0% schema description coverage across 8 parameters, the description compensates partially: it explains that email_account_id or email_account_uuid identifies the mailbox (mutually alternative), that recipients may be empty, and that fields mirror send_email. It says nothing about address formats, the distinct role of signature, or text-body expectations, so several parameters remain undocumented.

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 (save) and resource (an e-mail draft) and pins the destination to the mailbox's DRAFT folder, explicitly clarifying it does not send. The contrast with send_email ('same fields as send_email', 'without sending it') lets an agent distinguish intent without opening the 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?

Clearly frames the use case: compose-but-don't-send so a person can review and send from the panel, and references send_email as the related operation. It lacks an explicit 'use send_email instead when you want immediate delivery' routing sentence, but the context is unambiguous.

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