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

With no annotations at all, the description carries the full burden, and it delivers meaningful behavioral facts: spend has 'no metered overage exists; Builder has no ceiling,' units_saved is explained as the nominal weight cache hits would have cost, and money_saved_cents is tied to rate_basis ('plan or pro_reference'). The only gap is that read-only/auth behavior is implied rather than stated outright.

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 dense but well front-loaded, opening with the core purpose before diving into report specifics. Every clause earns its place, though the four report modes are packed into one semicolon-heavy paragraph where bullets would have improved scannability.

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 no output schema, the description does the necessary work of explaining return content for all four report types, including edge semantics like quota-exhaustion risk and the no-ceiling behavior. Minor gaps remain: authentication requirements, error behavior for invalid report values, and how window interacts with each report beyond 'ignored for spend' are not addressed.

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 coverage is 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema's terse 'One of: latency, errors, spend, cache' by specifying exactly what each report value returns (e.g., 'per-chain p50/p95 per bucket + summary'). It also reinforces a schema fact, that window is ignored for spend, which helps agents pick the right arguments.

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 opens with a clear statement of what the tool does: 'Windowed statistics for the authenticated account,' anchored to 'the console's Statistics pages,' and enumerates four report modes (latency, errors, spend, cache) with concrete metrics. It is clearly a statistics retrieval tool, but it never explicitly differentiates itself from the closely named siblings usage_report and usage_volume, so an agent must infer the distinction.

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 context is implied through the detailed report-mode breakdown: an agent can tell that this tool serves latency/error/spend/cache statistics needs. However, there is no explicit when-to-use or when-not-to-use guidance, and no mention of alternatives like usage_report, usage_volume, or billing_status, which overlap in the usage/billing domain.

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