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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds value beyond the annotations by disclosing the auth requirement (`read` scope) and the fact that it is scoped strictly to the calling key. It does not mention rate limits or caching, which keeps it short of a 5.

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?

Two compact sentences: the first front-loads what is returned, the second adds endpoint and auth constraints. Every clause carries information with no filler or repetition of the title.

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 helpfully enumerates the payload fields (queries, tokens, cost, budget remaining), which compensates for the missing return contract. Auth requirements and scope are covered. It stops just short of fully adequate because response shape, units, and pagination or time-window behavior remain unstated.

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 100% and the single optional enum parameter (`period`, default `current`) is fully documented in the schema. The description adds nothing about the parameter's semantics, so the baseline of 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 (Get) and resource (usage, quota, spend) plus the exact scope (the calling key), and enumerates the returned data (queries, tokens, cost, budget remaining). It even maps to GET /v1/usage, so an agent knows precisely what the call does and that it cannot target another key. Sibling tools (sources, channels, transcripts) are obviously unrelated, so no disambiguation is needed.

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 states a precondition ('Requires the key's `read` scope'), which is genuinely useful selection context. However, it gives no explicit when-to-use framing, no exclusions, and no alternatives to prefer. Usage is implied by the name rather than explained.

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