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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the description is not carrying the safety burden alone. It still adds meaningful context beyond them: an outbound SMS is sent to a real phone, and the tool is only half of a two-step flow requiring a user-supplied code. Rate limits, code expiry, and resend behavior are not disclosed, which keeps it from a 5.

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?

Two sentences, zero filler, with the action front-loaded and the required next step immediately after. Nothing could be cut without losing information.

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 one-parameter tool with no output schema, the description covers what it does, the external side effect, and the mandatory follow-up call. Minor gaps remain around failure handling and code lifetime, but an agent has enough to invoke it correctly.

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 coverage is 100% and the single parameter is fully documented with E.164 format and an example. The description only says 'phone number' and adds no format or normalization guidance beyond the schema, so the 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 ('Text a verification code to a phone number'), and the follow-up sentence separates it from the sibling verify_phone that consumes the code. An agent can distinguish it from request_email_verification or verify_phone 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 the sequencing rule explicitly: send the code, then ask the user for it and call verify_phone. That is real usage guidance for the tool's place in a flow. It stops short of saying when to prefer this over request_email_verification or how to handle re-sends, so not a 5.

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