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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior the annotations cannot: 'Each agent run holds credits first and settles to what the model actually used', which explains why balances may look momentarily reserved rather than settled.

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?

Front-loaded with the core noun phrase ('The active workspace's AI credit balance') followed by a compact enumeration and one clarifying sentence about settlement. The middle enumeration is a long comma run-on, but every item listed is information the agent would otherwise lack.

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?

There is no output schema, so the description must carry the return shape, and it does: available credits, monthly allowance, trial credits, purchased packs, reset timing, purchasable packs, and recent ledger lines. What it lacks is any indication of units, magnitude, or how much ledger history is returned.

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; the baseline of 4 applies. The implicit 'active workspace' scoping is the only parameter-like concept and is stated in the description.

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?

States a specific verb and resource ('get ... AI credit balance') scoped to 'the active workspace', then enumerates the components returned. It does not distinguish itself from the potentially overlapping sibling get_entitlements, so an agent must infer the boundary.

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 by the content described — there is no explicit 'use this when…' clause, no exclusion, and no pointer to an alternative such as get_entitlements. For a zero-parameter read tool the implied use is fairly obvious, but nothing steers the agent between competing lookups.

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