launch_app

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that relaunching stops the old copy, waits for the first load, and describes the replay action envelope. It does not cover failure modes or permissions, but it does disclose key side effects and timing behavior beyond the basic 'start' action, which is more than typical.

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 well-organized, starting with the core purpose in the first sentence, then dedicating a paragraph to each parameter. It is fairly concise for the amount of information conveyed, though it could be slightly trimmed without losing value. The structure aids comprehension, and the content justifies its length.

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 tool with three parameters, no annotations, and no output schema, the description covers the launch process, parameter semantics, and replay behavior. It hints at the return envelope but does not detail the exact output format or error handling. Given the complexity, it provides nearly all necessary context for an agent to invoke it correctly, though minor gaps (e.g., prerequisites like R/Python) remain.

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 explain all parameters. It does so thoroughly: `path` is defined as a folder (app.R, ui.R + server.R, app.py) or file; `interpreter` overrides the Rscript or Python executable; `replay` explains the replayed actions and the envelope. Each parameter's meaning and usage is clearly articulated, fully compensating for the schema gap.

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 verb and resource: 'Start the Shiny app at `path` and open it in a browser, then wait for the first load to settle.' It clearly distinguishes itself from siblings like stop_app and attach by describing the launch behavior. The purpose is unambiguous and specific.

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 clear context for when to use it, such as explaining that relaunching the same path stops the old copy (use after a crash or code change). It does not explicitly name alternatives or exclusions, but the guidance on relaunching and replay gives practical usage direction. A score of 4 reflects clear context without explicit when-not-to-use.

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