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

Annotations already declare destructive, openWorld and non-idempotent, but the description adds materially new facts: the send is irreversible, it may spend wallet funds, and ambiguous outcomes must not be auto-retried. Those are exactly the operational risks an agent needs before invoking a spend-capable, non-idempotent tool.

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?

Three short sentences, front-loaded with the usage trigger, then confirmation prerequisite, then the irreversible/retry risk. No filler and no repetition of schema details.

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?

An output schema exists so return values need no explanation, and the description covers auth, confirmation, cost and retry policy. It leaves a small gap: it does not point to get_sms_status as the way to resolve an ambiguous result, which is the exact scenario it warns about.

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%, so both recipient and message (with min/max length) are already documented. The description only adds a geographic constraint on the recipient that the schema example implies anyway. Baseline 3 with the schema doing the heavy lifting.

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 SMS) plus scope constraints: an authenticated SIMcloud user, a confirmed message, and a South African recipient. This is clearly distinguishable from siblings like get_sms_status or create_airtime_order.

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 preconditions: authenticated user, confirmed recipient and message, South African destination. It also warns against automatic retry on ambiguous results. It stops short of naming the alternative (get_sms_status) for verifying an ambiguous send, so the routing guidance is implicit rather than explicit.

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