start_cultivation

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

With no annotations, the description must fully disclose behavior. It mentions setting up installation, MCP config, first artifact, and growth re-entry, but does not explain what side effects occur (e.g., creates resources, modifies user state, requires permissions). The vague phrase 'defaults to env config' hints at environment dependencies but lacks clarity. The tool's behavior remains opaque.

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 uses emoji and bilingual text, which adds visual clutter and redundancy. It has three short sentences but repeats information. While it is relatively brief, the front-loaded emoji and Chinese phrase may distract or confuse an English-based agent. It could be more concise by using only English and focusing on essential details.

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?

Given that an output schema exists, the description does not need to detail return values. However, it fails to explain what the artifact_name parameter does or what constitutes a valid name. The tool has only two optional parameters and a simple onboarding purpose, so the description covers the basic function but lacks depth on prerequisites or outcomes.

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%, so the description carries the burden. It defines both parameters (username and artifact_name) with bilingual explanations, noting that username defaults to environment config. This adds meaning beyond the schema's simple titles and default values. However, it does not specify constraints or valid values for artifact_name.

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 states it is a 'first-session onboarding card for new TianGong users' and mentions setup tasks (installation, MCP config, first artifact, growth re-entry). This clearly identifies the tool's purpose as initiating the cultivation process for new users. The verb 'Start Cultivation' is specific and distinct from sibling tools like forge_agent or refine_agent, which focus on later stages.

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 implies usage for new users ('first-session'), but does not explicitly state when to use this tool versus alternatives. No exclusions or contrasting guidance is provided. Sibling tools cover different onboarding or growth activities, but the description fails to guide an agent on selecting this tool over others.

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