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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the bar is lower, yet the description adds real context: read-only and free, sign conventions for spend/refund/reversal, that balance and ledger are adjacent reads rather than one snapshot, and how to treat a ledgerUnavailable result. It also says to read the sign rather than trust labels, which prevents a costly misinterpretation.

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 what is returned, then usage and caveats, with no filler sentences. Slightly long and the Meta/Google ad spend caveat, while useful, drifts from the tool's core purpose; a tighter single clause would have sufficed.

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?

Output schema exists, so return values need not be re-explained, but the description still covers the edge case an agent must handle (ledgerUnavailable) and the 'adjacent reads, not a snapshot' caveat. For a zero-param read tool this is complete.

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 to disambiguate and the baseline is 4. The description instead documents the return payload fields (ledger sign, reason, resulting balance, spend receipt id), which is useful but partially overlaps the existing output schema.

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 (read) and concrete resources: credit balance, current plan (tier, state, renewal, monthly allotment), and recent ledger rows with named fields. There is exactly one wallet tool among the ~300 siblings, and the scope is unmistakable.

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 explicit when-to-use triggers: check balance before starting video generation runs so work does not stop midway, and read the ledger after a failed or interrupted generation before reporting cost. It also excludes a common misconception (wallet credits do not cap Meta/Google ad spend).

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