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

Annotations only supply generic flags (openWorldHint=false, destructiveHint=false), so the description carries most of the load and does add real context: results are bucketed by event recorded_at rather than meter creation time, per-bucket breakdowns by consumer_class/channel/provider are included, and est_accrued_minor is explicitly an estimate rather than authoritative billing. That estimate caveat is the kind of behavioral disclosure an agent needs to avoid reporting wrong numbers.

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?

A single dense paragraph, with the most important fact (recorded_at bucketing, UTC, bucket=day|hour) front-loaded and the billing-estimate caveat placed last where it belongs. 'a real time-series primitive' is mildly rhetorical but earns its place as sibling differentiation.

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?

An output schema exists, so return-shape explanation is not needed, and the description covers the computation and the estimate caveat. However, with 8 parameters at 0% schema coverage and no required fields, an agent still lacks guidance on date-range formatting and the include_test/meter_id filters, which is a meaningful gap for a query tool of this breadth.

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 0%, so the schema provides only titles and defaults (since, until, bucket, channel, meter_id, provider, include_test, consumer_class). The description compensates partially by documenting bucket's allowed values (day|hour), the grouping dimensions (provider, consumer_class, channel) and the recorded_at basis for date filtering. It says nothing about since/until format or semantics, meter_id scoping, or what include_test does, leaving half the parameters undefined.

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 names the resource (usage time series) and its defining computation: buckets keyed on each event's recorded_at, in UTC, with bucket=day|hour, grouped across meters by provider. It distinguishes itself from usage_summary by calling itself 'a real time-series primitive, independent of meter creation times,' so an agent can separate it from the sibling aggregate report without reading the 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 guidance is only implied: 'authoritative billing stays with usage_summary' routes the agent away from this tool for billing figures, which is a useful exclusion. But there is no explicit statement of when to choose this over list_events or usage_summary, and no prerequisites or typical call pattern are given.

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