Đổi gói MONA Mail

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true, so an agent knows this is a non-destructive, idempotent write. The description adds one genuinely useful behavioral fact beyond that: paid plans deduct from the VND wallet and insufficient funds triggers cloud_topup. However it omits What the cost is, whether the change is immediate, and what happens to existing mailboxes/data on downgrade.

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?

It is short, but it packs two languages and a payment-routing clause into a single slashed sentence, so it is not well front-loaded. The English half is the most generic sentence of the two, while the more useful Vietnamese half is deferred.

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-parameter write with a 0%-coverage schema, no output schema, and an opaque enum, the description is only partially adequate. It supplies the payment/insufficient-funds behavior, which is the most important non-obvious fact, but leaves the meaning of the plan values and the effect of switching unresolved.

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% for the single required 'plan' parameter, so the description carries the burden. It conveys that the plan determines whether payment is deducted (implicitly mapping to the free vs paid tiers), which is mildly useful, but it never enumerates or explains the enum values (free, khoi-nghiep, kinh-doanh, doanh-nghiep) or their quotas. The enum names themselves are opaque without explanation, so the description falls short of compensating.

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 English sentence 'Use to change the email plan' states a clear verb (change) and resource (email plan), and the Vietnamese adds detail about quota and selecting a plan. But it is not differentiated from the sibling mail_plans (which presumably lists plans), and the mixed-language, roughly-split phrasing makes the core purpose less crisp than a single clear statement would be.

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 does give a when-condition: 'when you need to change quota, select a plan,' and explicitly names an alternative for insufficient funds ('call cloud_topup'). That is real routing guidance. It stops short of 5 because it does not clarify when to use this vs. cloud_subscription_update or reveal prerequisites like verifying the target plan exists via mail_plans.

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