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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered elsewhere. The description adds genuinely non-structured context: the operation only produces a link for a human to complete, the agent itself charges nothing, and the "billing" scope is required. It does not mention link expiry or whether a repeated idempotency key returns the same URL, which would complete the picture.

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 compact sentences, front-loaded with what the tool produces before the constraint and the scope requirement. Every clause carries distinct information — artifact, cost behavior, bounds source, permission — with no restatement of the name or title.

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 tool with no output schema, the description covers the essential points: what is returned (a checkout link), that a human completes payment, the amount bounds and their source, and the required scope. Only edge cases such as link lifetime and idempotency-key reuse semantics are left unstated.

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 50%: only idempotency_key is documented in the schema, while amount carries just a minimum of 1. The description compensates by telling the agent that amount is bounded by the top-up limits published by list_services, which is information available nowhere in the schema. Currency/units of amount remain unspecified, keeping it below a 5.

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?

"A checkout link for a person to add funds to the API balance by card" names the concrete artifact produced (a link), the actor (the person, not the agent), and the resource (API balance). The clause "nothing is charged by the agent" separates it from the charging siblings (order, checkout_quote) without needing a schema lookup.

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?

It gives a real precondition — the amount must fall within the top-up limits that list_services exposes (orders.topup_min / topup_max) — and routes the agent to that sibling to obtain the bounds. What is missing is an explicit exclusion, e.g. when to prefer billing_portal_link or order instead of generating a top-up link.

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