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

With no annotations, the description carries the full burden. It discloses that the time series is bucketed by recorded_at (UTC, day/hour), is independent of meter creation times, includes breakdowns by consumer_class/channel/provider, and that est_accrued_minor is an estimate. This provides useful behavioral context, though it does not mention auth requirements or rate limits.

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 concise sentences that front-load the key information (time series bucketing, grouping, independence) and add supporting details (breakdowns, estimate note). Every sentence earns its place with no redundant or vague wording.

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?

Given the tool has 8 parameters, an output schema, and no required params, the description provides a solid overview of purpose, behavioral notes, and parameter roles. The output schema covers return values, so details on that are unnecessary. Minor missing details like date format or handling of missing data prevent a perfect score.

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 schema has 0% parameter description coverage, so the description must compensate. It explicitly mentions bucket (day|hour), channel, provider, and consumer_class, giving meaning to those parameters. However, since/until and include_test are only implicitly referenced, and meter_id is not addressed at all. The description adds value but leaves gaps.

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 clearly identifies the tool as a usage time series bucketed by recorded_at (UTC, day/hour), grouped by provider, and distinguishes it from usage_summary by noting that authoritative billing is elsewhere. It specifies the resource (usage timeseries) and the key breakdowns, making the purpose highly clear.

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 explicitly mentions that est_accrued_minor is an estimate and that authoritative billing stays with usage_summary, providing guidance on when to use this tool vs. the sibling usage_summary. However, it does not explicitly state conditions for using this tool over other siblings like list_events or verify_chain, though the time-series focus is implied.

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