Công cụ MONA app create

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

Beyond the annotations (readOnly=false, openWorld=true, destructive=false), it discloses meaningful behavior: first app host takes ~2-3 minutes, subsequent deploys 10-20 seconds, sandbox=true incurs no charge and creates no real infrastructure, and the caller must poll until done/succeeded. It also notes the cost-approval gate and the cloud_topup QR flow when credit runs out.

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?

The text is a dense bilingual wall of run-on prose, with Vietnamese immediately echoed in English, that reads as a full product workflow rather than a tool definition. It is not front-loaded around the tool's own action and drifts far into sibling workflows (domains, top-up, Base) that belong elsewhere.

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 14-parameter mutation tool with no output schema and near-zero schema coverage, the description should pin down parameter meaning and the result contract; instead it describes an orchestration script. It is incomplete precisely where the structured data is weakest, despite being verbose where the agent needs least.

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 7% across 14 parameters, so the description carries the burden and largely fails it. It mentions local_dir, repo_url, sandbox and app_host_id in the workflow, but env, name, port, wait, branch, domain, build_type, dockerfile, timeout_sec and interval_sec are undocumented in both places.

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 opening line states it is a compatibility alias of cloud_app_create, and the body makes clear the operation is creating/hosting an app from a git repo or local directory and returning its URL. The verb+resource are identifiable, though the workflow narration buries them rather than leading with them.

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?

It gives real routing guidance: use cloud_app_detect first, try sandbox=true before sandbox=false for cost estimation, obtain human cost approval once, and explicitly 'không gọi agent_deploy cho deploy dự án' (do not call agent_deploy for project deploys). That is an explicit exclusion plus a named alternative sequence. It lacks a crisp when-not-to-use, but the context is well covered.

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