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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful pre-call context: the auth requirement (API key or connected account) and the fact that results span every member and key rather than the caller's own activity. It doesn't describe pagination or volume limits, keeping it out of the 5 band.

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?

Three short sentences, front-loaded with what is returned, then when to use it, then the prerequisite. Every sentence carries information; the only mild duplication is restating the default that the schema already declares.

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 carries the burden of describing returns, and it does so adequately: daily granularity, grouped by op, with cache hit counts, org-wide. The unit of "usage" (requests vs. cost) is only implied by the bill reference, which is the one remaining ambiguity for a single-parameter read tool.

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?

There is a single parameter and schema coverage is 100%, with the schema already documenting the default of 30 and the 1-90 bounds. The description repeats the default and calls the value "N" but adds no new syntax or interpretation beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb+resource (retrieves the organization's daily usage for the last N days) plus the aggregation dimensions: by op, cache hit counts, across every member and key. That granularity separates it in spirit from list_audit_log or get_billing_link, though no sibling is named explicitly.

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?

"Use it to explain a bill or spot a runaway client" gives two concrete use cases, which is clear context for selection. It stops short of naming an alternative or a when-not condition, so it falls just below the top band.

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