snap_billing_check

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds genuinely new behavior context: the auth prerequisite ('a login that can see the organization's funding sources') and the fact that a computed verdict, not raw fields alone, is returned. It stops short of saying how stale the figures are or what happens when funding data is unavailable to the credential.

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?

It opens with the decision question the caller cares about, then the data scope, then the auth caveat — good front-loading with no filler sentences. The long parenthetical enumeration is dense and slightly hard to scan, which keeps it from a 5.

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 carries the return-value burden and does so by listing the funding dimensions and the verdict, plus the credential requirement. Minor gaps remain around freshness of the figures and failure modes, but nothing needed to invoke it is missing.

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 the baseline is 4 and there is nothing about argument meaning that the description could or should add. The parenthetical does describe what is measured internally, which is useful framing for the verdict even though it is not parameter documentation.

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 names a specific question the tool answers ('Will ads keep running?') and then enumerates exactly what is inspected: ad account status, funding sources (card expiry, daily spend limit vs. active ad squad budgets, line-of-credit remaining and days covered), and a verdict. That is far more specific than the sibling health/status tools and an agent can tell what data comes back without opening anything else.

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?

Usage is implied by the framing question — you call this when you need to know whether delivery will be interrupted by billing problems — but there is no explicit when-to-use/when-not-to-use statement and no named alternative (e.g. a general health check) to contrast against. The reader must infer the trigger condition.

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