Công cụ MONA base create

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

Annotations already declare this is a mutating, non-idempotent, open-world call. The description adds real behavioral context beyond them: the tool polls the job to completion (long-running/blocking), it checks the wallet (billing implication), and sandbox mode returns an estimate without creating infrastructure. It omits any warning that non-idempotent retries could bill or create twice, which is the one gap keeping it from a 5.

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?

Front-loaded with the workflow, which is good, but the bilingual text is not a clean mirror: the Vietnamese line and the two English lines repeat the same 'Base beta / Supabase replacement' idea twice, and the third sentence adds nothing new. Compact overall, but one sentence does not earn its place.

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 create tool with no output schema, zero required params, and 17% coverage, the description covers the process and the sandbox branch but leaves key agent needs unanswered: what job identifier or resource is returned, whether the call blocks, and what happens on timeout or failure. Adequate but with clear gaps.

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 only 17% – just the sandbox flag is documented. Six parameters (cpu, ram_gb, disk_gb, plan_code, billing_mode) carry no description in either the schema or the description text, and the description adds no meaning about units, defaults, allowed ranges, or how plan_code interacts with billing_mode. With low coverage the description was obliged to compensate and does not.

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+resource ('tạo Base' / 'create the Base') and even describes the full workflow (estimate, wallet check, create, poll). It is clearly distinguishable from cloud_base_list/get/delete/credentials by the create verb. It never names a sibling explicitly, so it falls short of a 5.

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?

Implies when to use it (when you need a Base provisioned) and adds one useful conditional: 'sandbox chỉ trả ước tính' / 'Sandbox estimate only'. But there is no explicit when-not, no prerequisites, and no routing to alternatives such as cloud_base_get for checking an existing Base or cloud_balance before spending.

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