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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description explains the idempotency MECHANISM (client_ref reuse returns existing order without second charge), the 429 rate limit (50 orders/24h per wallet), the 402 error meaning, and the pricing rule (price × days). These are behavioral facts the annotations cannot convey. No contradiction with annotations.

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?

Dense but front-loaded and waste-free: the core purpose leads, followed by idempotency, parameter semantics, return flow, error handling, rate limit, and prerequisite. Every sentence carries operational value for a tool with this many behavioral gotchas; nothing is filler.

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 6-parameter mutating tool with idempotency, rate limits, plan-specific pricing, and an error path, the description covers the full call lifecycle: prerequisite (wallet code), action, parameter constraints, response handling (poll get_order), failure handling (402 → create_deposit), and throttling (429). The existence of an output schema relieves it from documenting return shape in detail.

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 0%, so the description carries the full burden, and it delivers: client_ref gets length, purpose, and idempotency semantics; period_num gets range, default, applicability (daily_unlimited only), and cost formula; topup_iccid gets its pairing with list_topups that an agent could not derive from the bare schema titles. Minor gaps remain for lang/email and the source of plan_id in the non-topup path, but the semantically critical parameters are fully explained.

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 opening clause 'Charge the wallet and issue an eSIM, no checkout' names a specific action and resource and immediately distinguishes this direct-purchase path from the checkout flow (create_checkout). The purpose is unmistakable even before reading parameter details.

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?

The description names concrete alternatives with their trigger conditions: 'create_deposit first' on a 402 short-balance, 'plan_id from list_topups' to top up, and 'poll get_order(token)' after purchase. 'No checkout' and 'Needs the wallet code' frame when this tool is and is not the right choice. Nothing is left to inference.

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