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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this with 'Free; changes nothing' plus a useful cost note. It also discloses a visibility nuance ('shown to the Owner') and that the spend cap is scoped to the API key this connection uses, which annotations cannot convey. It stops short of stating freshness/latency of the reported figures or pagination-free return shape.

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?

The scoping statement and the usage triggers come first, and the NOT-for clause closes it cleanly. The opening sentence is a long comma-chained list of five returned items, but every element is a distinct fact an agent would otherwise have to guess at.

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 output schema, the description carries the burden of describing return contents and does so explicitly (balance, holds, settled spend, cap, top-up). Zero params plus a read-only purpose means nothing else is needed for correct invocation.

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 is 4. The description still clarifies that scope is implicitly the current connection's workspace/API key, which is the only 'implicit input' an agent could get wrong.

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?

Names a specific resource (prepaid balance) and enumerates exactly what is reported: USD balance, in-flight holds, settled spend today/this month, daily spend cap, top-up location. It also pre-empts confusion with the sibling by excluding per-run pricing and naming capability_inspect.

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?

Gives two concrete triggers (a run refused for funds; before a job that will make many runs) and an explicit exclusion with the correct alternative tool. Nothing about when to reach for it versus capability_inspect is left to inference.

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