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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds context beyond that: an authorisation prerequisite (owner/admin) for the pooled view and a semantic clarification that counts are not charges, which prevents a common misinterpretation of the result.

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 sentences, no filler, with the primary scope stated first and the organisation variant plus the interpretive caveat following. Every clause carries information an agent needs.

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?

For a one-optional-parameter read tool, the description covers purpose, both scope options, the role requirement for the org view, and the meaning of the returned counts. The output schema handles return structure and annotations handle safety, so nothing material is missing.

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 0%, so the description has to carry the meaning of 'view', and it does: 'your usage' maps to the user enum value and 'pooled organisation usage' plus the owner/admin qualifier maps to the organization value. The enum names are not literally restated, but each option's semantics and access requirement are conveyed.

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 and resource ('Read your usage') and names the two scopes it can cover: per-entry-point user usage and pooled organisation usage (owner/admin), enumerating jobs and credits as the measured quantities. It also pre-empts confusion with billing by noting request counts aren't charges, though it does not name a sibling outright.

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?

Gives the condition that selects the organisation scope (owner/admin role), which is genuine when-to-use guidance for the single parameter. It stops short of saying when to prefer this over get_billing or get_activity, so an agent must infer the boundary from the closing caveat rather than an explicit routing statement.

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