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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description only needs to add context beyond that. It does: newest-first ordering, cursor-based pagination, the exact ledger entry categories returned, and the read_usage scope requirement — all things annotations cannot express. It stops short of describing entry fields or pagination termination behavior.

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?

Three compact sentences, zero filler, and the core identity (ledger + ordering + pagination) is front-loaded before the query and scope details. Every clause carries information the agent needs.

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 usefully enumerates what a ledger entry represents (debits and credits of four types), covers ordering, pagination, and auth scope. It is nearly complete for a read-only list tool; only the shape of individual entries and end-of-pagination behavior are left unspecified, which is a minor 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?

Schema coverage is 50% (only cursor is documented in the schema). The description compensates meaningfully by giving the limit range (1–100) and by explaining that cursor is a created_at value taken from next_cursor, which is a semantic detail the schema does not provide. Default page size is left to the 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+resource (the account's credit ledger), plus its contents (generation charges, refunds, plan allocations, top-ups), ordering (newest first), and pagination model. No sibling tool reads ledger data, and the description's specificity makes that separation obvious without opening any schema.

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 resource ('query the ledger for charges/refunds/allocations') and it names the required scope (read_usage), which is genuinely actionable. However, there is no explicit when-to-use/when-not-to-use statement or routing to an alternative view of the same data, so it stays at the implied-usage level.

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