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

The annotations already establish a safe, idempotent read. “Ne consomme rien” adds the important billing-specific guarantee that the call itself consumes nothing, although further operational details such as data freshness are not provided.

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-load the resource and end with the non-consumption guarantee. The semicolon-heavy conditional notation and phrases such as “« au quota » des coûts” are dense and require some parsing.

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 zero-argument read with an output schema and full safety annotations, this covers the meaningful response variants and the key side-effect concern. No additional input, return-format, or destructive-behavior documentation is needed to invoke it correctly.

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?

There are no parameters, so there is no input syntax or semantics for the description to clarify; the zero-parameter baseline applies. The response-field detail is useful but does not change that input assessment.

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 identifies the account and billing-state resource and details both credit-based and unit-quota states, distinguishing it in substance from the company and search siblings. It is a noun phrase rather than an explicit retrieval statement and does not name an alternative, so it stops short of the top score.

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 listed fields make the intended context clear: checking the billing model, credit balance or expiration, plan, and remaining company allowances. It does not explicitly recommend when to call it, such as before a consuming operation, or when another tool would be preferable.

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