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

Annotations already flag readOnlyHint=false, destructiveHint=true, openWorldHint=true; the description reinforces this with far more useful detail: delivery is immediate, cannot be recalled, and the backend validates eligibility for the recipient. That is exactly the consequence-level context an agent needs before a destructive outbound action.

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 the action and its irreversible nature, then the confirmation requirement. No restated name/title, no filler; each sentence adds a distinct operational fact.

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 two-parameter outbound mutation with no output schema, the description covers everything that matters: eligibility validation, irreversibility, and the mandatory confirmation step. Nothing an agent needs to call this safely is missing.

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 100% and both parameters (message, phoneNumber in E.164) are documented there. The description only adds that the recipient must be messaging-eligible, which is a constraint rather than parameter syntax, so baseline 3 applies.

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 ('Send an SMS') with scope ('a phone number that is eligible for messaging'). The phrase 'REAL ACTION, not a preview' directly separates it from preview/confirmation-style siblings such as previewReceptionistGreeting, so an agent can classify it 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?

Gives a clear precondition for invocation: show the exact recipient and message and obtain explicit user confirmation immediately before calling. It also frames the not-a-preview case. It stops short of naming a sibling alternative for non-delivery scenarios (e.g., drafting vs sending), so it is clear context rather than a full when/when-not decision tree.

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