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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds real context beyond that: calling consumes no GPU time (so it is safe to poll), the data is scoped to "this key", and the response may contain a tell_user field that must be relayed to the user in their language — a non-obvious behavioral requirement. Return shape itself is left to the output schema.

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?

A single sentence, front-loaded with the outcome the caller cares about (what remains free) followed by a compact colon-list of returned fields. Every clause carries information — no filler. The list is long, but each item is a distinct returned value an agent would otherwise have to discover from the schema.

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 an output schema present the description need not describe return values in detail, and annotations cover the read-only/idempotent profile, so the essentials are in place. The one thing an agent must know that no structured field conveys — that tell_user should be surfaced to the user in their language — is stated explicitly. Minor gap: no note on whether the key/plan is required or what happens when the key has no credit.

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 no parameter semantics to explain and the baseline of 4 applies. The description correctly spends no words on arguments and instead documents the response content.

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 opens with a concrete verb and resource ("Check what this key can still render for free and its credit") and then enumerates exactly what the call returns: free GPU time and expiry/reset, balance, price per GPU-second, pending checkout link, applicable offers. This is far more specific than the bare name/title. It stops short of naming the sibling it is not (e.g. render_estimate, which is the closest source of confusion for cost questions), so it is clear but not sibling-differentiating to the highest degree.

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 purpose implies when to reach for it (checking remaining free quota/credit before rendering), and "(no GPU time)" hints that it is cheap to call. But there is no explicit when-to-use/when-not guidance and no mention of the alternative tool (render_estimate) for per-render pricing. The final sentence about relaying tell_user is an output-handling instruction, not usage scoping.

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