cloud_app_create

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

With no annotations provided, the description carries the behavioral transparency burden and does add useful non-obvious details: first host creation takes ~2–3 minutes while later deploys take 10–20 seconds; sandbox=true is free and creates no real infrastructure; cost approval is needed only once; and the workflow polls until done/succeeded. It does not cover error behavior, authentication prerequisites, or edge cases like the relationship between local_dir and repo_url, but it discloses the most consequential behaviors.

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 description is dense, repetitive, and mixes Vietnamese and English, duplicating the same workflow in prose and in the final English summary. It reads as a process narrative rather than a tool definition, and the first sentence focuses on timing ('App từ git đã live...') instead of a clean purpose statement. It would benefit from a short definition followed by essential workflow notes.

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 complex 14-parameter tool with no annotations and no output schema, the description is not complete enough for reliable invocation. It does provide helpful end-to-end context around sandbox estimation, cost approval, polling, and returning a URL, but it leaves major gaps around required inputs, build configuration, wait/timeout behavior, and the exact response shape. An agent would still have to guess about many parameters.

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%, with only sandbox described in the schema. The prose adds meaning for sandbox=true/false and mentions local_dir, repo_url, and domain, but the remaining ~11 parameters (name, port, wait, branch, build_type, dockerfile, app_host_id, timeout_sec, interval_sec, env) are left entirely undocumented in both the schema and the description. This is a significant gap for a 14-parameter tool.

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 description conveys that this tool creates and deploys a cloud app from a local directory or git repository and returns a URL, especially via the English summary 'upload and deploy, return URL, then attach an optional domain.' It distinguishes itself from agent_deploy by explicitly saying 'không gọi agent_deploy cho deploy dự án.' However, the core purpose is embedded in a long, multi-step workflow rather than stated as a crisp one-line definition.

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 provides an explicit workflow: run cloud_app_detect locally, check host/prices/balance, create with sandbox=true to estimate cost, get human approval, create with sandbox=false, poll until succeeded, and optionally add a domain. It also gives a clear exclusion: do not call agent_deploy for project deployment. It does not contrast with cloud_app_deploy, but it gives enough context for when to use this pipeline.

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