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

Annotations declare destructiveHint=true and non-idempotent, but the description adds far more: wallet debit, automatic refund within 10 minutes for unfilled orders, no penalty for retrying, and an explicit 'this spends real wallet balance' warning. It also corrects a likely wrong agent instinct (do not cancel to retry), which no structured field conveys.

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-loaded with the core action and return values, and nearly every sentence carries operational guidance rather than filler. It is dense and slightly long, and the spending warning sits at the end rather than up front where a cost warning would be most salient.

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?

There is no output schema, and the description compensates by naming the returned fields and describing downstream flow, refund timing, retry policy, and pool selection. An agent has everything needed to call this correctly and handle the failure case.

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 the country and service semantics are already documented, making 3 the baseline. The description goes beyond the schema by advising which pool to choose when a service rejects codes — 'us1 (Non-VoIP AT&T) pool, which has the highest delivery rate' — adding decision-level meaning the schema only partially implies.

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?

The first sentence names a concrete verb and resource ('Buy a number to receive an OTP'), lists the side effects (allocates a number, debits the wallet), and states the return shape (orderId + phoneNumber). It also names the follow-up sibling poll_sms, so an agent can distinguish the ordering step from the polling step without opening either 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?

Explicit guidance is given for the full lifecycle: call this, then poll with poll_sms; if no code arrives, do NOT cancel to retry, instead call create_otp_order again. It also states the escalation path (use the us1 pool when a service keeps rejecting codes) and the cost condition (auto-refund within 10 minutes means repeated ordering carries no penalty).

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