Summarise usage

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

Annotations already cover read-only and idempotent behavior. The description adds useful behavioral context beyond annotations by stating the required authorization scope and clarifying output semantics: 'total_micros is micro-USD; total_display is human-readable.' This meaningfully supports correct invocation and interpretation.

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?

The description is three terse sentences: the first states purpose, the second explains output fields, and the third gives an auth requirement. There is no filler or redundancy; every sentence earns its place.

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 simple two-optional-parameter read tool, the description covers the core purpose, grouping dimensions, output field units, and required scope. Since there is no output schema, the response structure is only partially explained—e.g., how the breakdown by component/provider/model is shaped—so it is strong but not fully 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 input schema already fully describes both parameters with 'Period end. Defaults to now.' and 'Period start. Defaults to the start of the current month.' The description does not add date format, syntax, or other parameter-specific details, so it stays at the baseline for high schema coverage.

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 states a specific verb and resource: 'Total spend over a period, broken down by component, provider and model.' This clearly distinguishes the tool from siblings like list_usage_events or get_balance, even without naming them, because it defines exactly what summary it produces.

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 description implies when to use the tool—when you need a spend summary over time—and includes a prerequisite ('Requires scope usage:read'). However, it does not explicitly contrast it with alternatives such as list_usage_events for raw events or get_balance for current balance, so usage guidance is only implied rather than explicit.

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