get_usage

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

readOnlyHint=true already declares the safety profile, and the description adds genuinely non-redundant behavior: the account-level auth requirement and the fact that completing start_login will not unlock this tool. It does not mention rate limits, error modes, or pagination, but for a read-only metrics call those gaps are modest.

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 tight sentences with the purpose front-loaded and the access constraint clearly separated by an 'ACCESS:' label, so the agent can scan it quickly. The environment-variable advice is slightly verbose for a mid-session caller, but it earns its place as a prerequisite.

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 read-only metrics tool with full schema coverage, the description covers what is measured and the account prerequisite. With no output schema, it should ideally say more about the returned metric shape or whether months/period are exclusive; that is the main residual gap.

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% – both 'months' (1-12) and 'period' (YYYY-MM) are fully documented with format and bounds in the schema. The description adds nothing about them, notably not whether months and period are mutually exclusive or how they interact. Baseline 3 when the schema carries all parameter meaning.

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 ('Get usage metrics for the authenticated account') and enumerates the payload (verification counts, API calls, quota usage), so the agent knows what it returns. It does not distinguish itself from close siblings such as get_api_key_usage or get_platform_summary, so a routing agent must still guess which usage view it wants.

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 a concrete prerequisite (needs a Proof account, PROOF_API_KEY must be set with a server restart) and an explicit negative case: 'start_login does NOT open this tool,' which closes off a plausible but wrong path. It stops short of naming alternatives like get_api_key_usage or get_platform_summary for narrower/aggregate usage views.

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