Get Email Usage

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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: the data is refreshed hourly (staleness caveat) and results are sorted largest-first. It doesn't discuss truncation or limits for accounts with very many mailboxes.

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 and in what order, followed by the use case and the freshness caveat. Every sentence carries information an agent would otherwise lack.

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 zero-parameter read tool with an output schema, this covers nearly everything: scope, ordering, field set, use case, and refresh cadence. The only gap is whether results are ever truncated or capped for accounts with many mailboxes, which matters given there is no pagination parameter.

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 no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly signals that the response is account-wide and unfiltered.

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 ("Returns per-mailbox disk usage for the account") plus the ordering (largest first) and returned fields (email address, size in bytes, last update time). This is distinguishable from the sibling get_disk_quota, which covers account-level quota rather than per-mailbox consumption.

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 use case: finding mailboxes to trim when the account nears its quota. It doesn't explicitly name alternatives or exclusions (e.g., how it differs from get_disk_quota or list_email_accounts), so it stops short of full routing guidance.

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