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

Annotations already declare destructive/non-idempotent, but the description adds substantial context they cannot convey: credits are consumed, sends cannot be recalled, execution is asynchronous, unsubscribed addresses are skipped, and the account owner's email must be confirmed first. These are exactly the operational risks an agent needs before invoking.

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-loads the critical destructive warning and keeps every clause factual with no filler, though it is a single dense paragraph — the confirmation rule and the mode selection would read better as distinct lines rather than buried mid-block.

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 14-parameter, irreversible tool with no output schema it covers prerequisites, limits, mode selection, and where results land. The gap is the return shape: it says results appear in the transactional group but never states what the call hands back (send IDs, per-recipient statuses), so an agent must infer success handling.

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 64% schema coverage the description earns its keep by explaining the recipient identity rule (exactly one of contact_id/email/mobile), the 100-recipient cap, positive wildcard syntax (%%key%%) tied to the data object, and the message_id-versus-custom-content exclusivity. Secondary fields such as from_name, reply_to, unsubscribe_type and group_id are left entirely to the schema.

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 an explicit verb and resource ('SENDS REAL EMAIL OR SMS') and immediately marks it as a write with immediate, irreversible effect. That distinguishes it cleanly from the message-creation siblings (vision6_create_message) and the read-side tools in the list.

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?

It lays out the decision branches explicitly: saved message via message_id versus custom content, email requiring list_id, SMS requiring body_text plus from_address. It also states the confirm_send precondition ('only after the user approved these recipients and this content') and points to vision6_get_transactional_group for follow-up.

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