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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description contributes the scope detail that figures are per billing period (period-scoped, account-level), which is real added context, but it says nothing about whether values are cached, refreshed, or whether the account scope is the caller's workspace.

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?

A single compact sentence fragment with no filler, and the most important item (plan) is front-loaded. The lack of a leading verb makes it slightly less scannable than it could be, but nothing is wasted.

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 parameters and no output schema, the description carries the burden of indicating what comes back, and the field enumeration (plan, runs used, included runs, extra-run packs, runs left) does that adequately for a simple read. It is complete enough to call correctly, though it never states the unit/account scope explicitly.

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?

The tool takes zero parameters, so the baseline is 4; the schema is empty and complete, and there is no parameter meaning for the description to add or omit.

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 enumerates what the tool surfaces ('Plan, runs used this billing period, included runs, extra-run packs and runs left'), which tells an agent it is a billing/usage summary rather than a build or project lookup. However, it is a bare noun list with no verb and no explicit statement that it retrieves account usage, so it largely restates the name 'get_usage' plus its fields rather than crisply defining the operation.

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?

There is no guidance on when to call this versus siblings such as get_project, list_runs, or get_build — an agent must infer that this is the quota/billing view. No preconditions, no exclusions, no mention that it takes no arguments.

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