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

Goes well beyond the annotations: real cost ('billed by provider'), a hard recipient cap of 50, opt-out skipping, country-code inference for numbers prefixed with a single 0, and per-recipient outcomes. These are exactly the side effects an agent needs for a destructive, non-idempotent send.

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 warnings (real SMS, billed, 50 cap) and packs the content-versus-template rule and country-code behavior efficiently. Parenthetical qualifiers are dense but every clause carries information; slight compression makes it read as a run-on.

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 destructive tool with no output schema, it covers cost, limits, recipient handling, and return shape ('one outcome per recipient'). Error modes such as invalid numbers or account-level failures are not addressed, which keeps this just under complete.

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 compensates: it explains the account identifier pair, the mutually exclusive body vs. template_id/uuid plus message_vars pattern, and the recipient-list semantics. It does not describe the structure or key expectations of sms_message_vars, leaving one gap.

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 and resource ('SENDS REAL SMS'), the per-call cap (50 numbers), the account requirement, and the fact it is billed. It is clearly separable from siblings like render_sms_template (preview) and send_email (different channel).

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?

Explicitly names the alternative for previewing ('Use render_sms_template first') and states the account must be ACTIVE. It gives clear context for use but does not spell out when NOT to send (e.g. opt-out handling is mentioned only as automatic behavior).

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