usage_attribution

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers exceptionally: it states 'Read-only' explicitly, reveals the two-orthogonal-metric quirk (5-25x apart), discloses the sub-agent coverage shortfall, warns that population paths are never merged, and explains why there's no total field (95.6% cache_read). This is deep, honest behavioral context.

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 lean and front-loaded, with the core purpose in the first sentence. Every subsequent sentence earns its place by clarifying a behavioral invariant (denominator/label pairing, two-metric gap, 95.6% cache_read, no total). It covers rich context without padding or repetition.

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 an output schema, return-value explanation is delegated. The description handles the complex semantics—dual metrics, sub-agent coverage shortfalls, population non-merging, windowing semantics—comprehensively, which is exactly the depth needed for a tool with these quirks. Combined with a 4-param all-optional schema, this is 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?

Schema coverage is 100%, so the schema already documents all 4 parameters thoroughly. The description reinforces key semantics by explaining the day-windowing rationale (never on measurement time) and the population non-merging invariant, adding meaning beyond the schema's field names. It doesn't need to over-compensate given full 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 gives a specific verb+resource ('Report token usage together with how much of it can actually be accounted for') with a clear, distinctive scope. It differentiates itself from read-report siblings by emphasizing the denominator/metric-label pairing and the deliberate absence of a total field, which makes this tool's unique role unmistakable.

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 clearly explains when usage makes sense (accounted-for token reporting) and the 'Read-only' framing signals safe usage context. It doesn't explicitly name alternative tools for token reporting, but it does clarify internal semantics (no total field, why denominators matter, why population is never merged) that guide correct invocation. Marginal missing piece is explicit when-not-to-use guidance against siblings.

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