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

Annotations already declare the tool read-only and idempotent, so safety details are covered. The description adds behavioral context beyond annotations by explaining that the output is normalized and that pagination is automatically drained, which is not visible from annotations or the schema.

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 concise and front-loaded with the primary purpose. The second sentence about pagination is valuable, though slightly jargon-heavy, but it still earns its place by letting the caller know pagination is handled internally.

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 six parameters, no output schema, and no per-parameter documentation, the description is too sparse to be fully actionable. It omits the output shape, what 'normalized' means, and how the date parameters relate, so an agent would likely need additional context to call the tool correctly.

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 six parameters with zero description coverage, and the description does not explain the meaning or interaction of start_date, end_date, days_back, group_by, bucket_width, or account. It only mentions 'date range,' leaving most parameter semantics uninferred.

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 states the tool retrieves normalized Anthropic Messages API usage for a date range. It specifies an action (get), a resource (usage), and a distinguishing qualifier (normalized, Messages API), which separates it from the sibling billing cost and account list tools.

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 usage is appropriate for date-bounded Messages API usage queries, but it gives no explicit guidance on when to choose this tool over the similar anthropic_billing_cost or anthropic_billing_list_accounts siblings. There are no stated exclusions or alternative recommendations.

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