make_script

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses cached API checks, the exact write path under scripts/, overwrite behavior, that unsupported prompt patterns fail without generating a file, that prompt numbers do not customize the template, and that the tool does not directly upload. These details give an agent the behavioral context needed to invoke it safely.

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 front-loaded with the action and scoping, followed by inputs, effects, constraints, and alternatives. It is dense but mostly earns its length, though the explicit list of return fields is somewhat redundant given the output schema exists.

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 the lack of annotations, an output schema, and many sibling tools, the description is complete enough for correct selection and invocation. It covers purpose, routing, inputs, effects, failure modes, and return shape without requiring the agent to infer critical constraints.

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 must compensate for the single prompt parameter, and it does. It states prompt is a required non-empty string, explains that supported patterns select among three fixed templates, and clarifies that prompt numbers do not customize the output and that supplied Lua code, directories, or filenames are not accepted.

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 a specific compound action: generate, save, and statically validate a fixed Lua starter template from a text prompt. It clearly differentiates this tool from siblings like create_script and create_project_script by scoping it to fixed starter templates rather than custom source. An agent can tell what the tool does without opening the schema.

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 explicitly says to choose this only when a fixed starter is sufficient and names the alternatives for custom Lua or a specific destination: create_script, create_project_script, or create_directory_script. It also routes complex mechanics to resolve_creative_mechanic and recommend_algorithm before authoring, giving clear when-to-use and when-not guidance.

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