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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description's real contribution is the credit-to-cent conversion, which tells the agent how to interpret the numeric result. It does not say whether the value is a snapshot, whether it can be negative, or what the response payload looks like, and with no output schema that is a remaining gap.

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 short sentence with no filler. The resource is front-loaded and the unit clarification follows immediately where it matters most.

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 authenticated read with rich annotations, the definition covers what the value means (credits, convertible to cents). What is thin is the return-value shape and lifetime — no output schema exists, so a brief note on the response fields or whether the figure is live would close the last gap.

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. Baseline 4 applies; the unit note is a bonus rather than a parameter explanation.

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 resource — 'The workspace's credit balance' — and disambiguates the unit with '(1 credit = 1 US cent)'. The retrieval verb is carried by the name/title rather than the description, and there is no sibling that returns balance data, so no differentiation statement is needed.

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 only implied: an agent infers it should call this when it needs the current credit balance. There are no prerequisites, no when-not-to-use note, and no mention of related siblings like estimate_run or create_topup_link that an agent might want in a balance-checking flow.

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