Billing Events

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuinely useful operational context the annotations don't: a 10,000-record page cap, a 90-day date-range cap, cursor pagination, and the shape of the per-record cost breakdown including the nano-USD field. It omits auth/permission requirements and default date-window semantics beyond brief hints.

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?

Well front-loaded: the core behaviour and returned fields come first, then bulleted features and use cases. It is somewhat padded — the 'Individual billing event records for each API request' bullet restates the opening sentence, and the use-case list is somewhat generic — but structure and scannability are good.

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 10-parameter read tool with no output schema, the description covers the pagination model, page/range limits, and the fields returned, which is enough for correct invocation. Missing pieces are minor: no explicit output envelope/pagination response shape and no note on what happens when no filters are supplied.

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 description coverage is 100%, so the schema already explains every parameter (dates, cursor, expand, api_key_id, request_id, endpoint_id, login_username, account) with formats and array syntax. The description adds little parameter-level detail beyond the 90-day range cap, which justifies the baseline 3 rather than higher.

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?

Opens with a specific verb+resource ('Returns paginated individual billing event records') and enumerates the returned fields (request ID, timestamp, endpoint, units, cost breakdown). It implicitly distinguishes itself from aggregate siblings like get_account_billing and get_usage by emphasizing 'individual ... records', but never names an alternative, so a perfect 5 isn't earned.

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?

The 'Common Use Cases' block gives concrete contexts (audit individual billing events, debug specific requests by ID, monitor unit consumption) that tell an agent when this tool fits. However, it provides no exclusions or routing advice against siblings such as get_account_billing or get_usage, so guidance is contextual rather than prescriptive.

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