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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the agent knows this is a safe, repeatable read. The description adds the useful behavioral detail that the tool exists to explain a prior 402 failure to the human. It does not disclose what data comes back, whether calling it has any cost, or what happens outside a 402 context.

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 say essentially the same thing: 'tell the user exactly what is missing' appears verbatim in both. The trigger is front-loaded, which is good, but the second sentence is pure redundancy and displaces content that would actually be useful, such as what fields are returned.

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?

With no parameters and no output schema, the description is the only source of information about the return payload, and it never states that the tool surfaces balance, plan tier, or remaining credits. For a diagnostic tool invoked under a 402, the agent needs to know what it will learn. The trigger guidance is complete; the result expectations are not.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. The baseline of 4 applies; the description correctly implies the tool is parameterless because it is scoped entirely by the caller's account context.

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 description frames the tool around its trigger condition ('when a call was refused for credits or plan') rather than stating plainly what it returns. The title 'Account balance and plan' carries most of the resource identification, while the body only says it will 'tell the user exactly what is missing'. An agent can infer it is a billing diagnostic read, but the purpose is described indirectly.

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 an explicit, concrete trigger: after a 402 refusal due to credits or plan. That is stronger than most definitions and tells the agent precisely when to reach for this tool. It stops short of naming alternatives (credits_balance, billing_plans) or stating when not to use it, so it is clear context without exclusions.

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