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

The description labels the tool "[read]" and asserts "nothing is sent or saved", but annotations declare readOnlyHint=false and destructiveHint=true. An agent cannot tell whether calling this mutates merchant state or is a pure draft helper. The rich content guidance does not offset a direct conflict on the safety profile.

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?

Front-loaded with the read/draft framing and the recipient/defaults rules packed into two long sentences; nearly every clause carries information. Punctuation in "customer_uuid) - Maps lists none" is awkward and slows parsing of the WhatsApp fallback.

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?

No output schema exists, yet the description discloses that the return value is ready send_email arguments, which covers the critical integration detail. Remaining gaps are precedence between recipient sources and whether the handwritten text is validated or templated.

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 the description carries the full burden and mostly does: it explains recipient resolution (`to` vs. e-mail embedded in the supplier customer's title/note via customer_id/customer_uuid), the mailbox defaulting for email_account_id/email_account_uuid, and what subject/text should contain. It does not state which source wins when both `to` and customer_id are supplied.

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?

Opens with a specific verb+resource ("Prepare a first-contact e-mail to a supplier") and immediately states the output shape: "Returns the ready send_email arguments - nothing is sent or saved." That differentiates it from send_email and save_email_draft without the agent opening any 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?

Gives explicit when-to-use guidance (first contact asking for prices / MOQ / lead time) plus a conditional alternative: when Maps lists no address and the supplier has only a phone number, use list_wp_templates + send_wp_template instead. It also states default behavior for the mailbox, so no inference is required.

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