run_python

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

With no annotations, the description carries the full burden and does most of it: discloses main-thread execution, unrestricted read/write/delete over anything Designer can access, and the important fact that the allowed-folders restriction does not apply inside the code. Minor gaps remain (execution timeout, stdout/exception handling), so not a 5.

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 safety-critical constraint is front-loaded in capitals, and each sentence carries distinct information. Slightly verbose in places (the danger notice and the fallback notice overlap conceptually), but no wasted sentences.

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 no annotations and no output schema, the description supplies the safety profile, the invocation gate, and the output convention (`result`). Only execution-environment details such as timeouts and error surface are unstated, which is acceptable but not exhaustive.

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 coverage is 0%, so the description must compensate. It fully explains the `confirmed` gate protocol and gives the runtime contract for `code`: the `sd` and `app` objects are available and `result` is the return channel. It does not explain code format constraints (imports, entry point), so it stops short of a 5.

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?

States a specific verb+resource ('Ejecuta codigo Python arbitrario dentro de Designer') and adds execution context (main thread). It also differentiates itself from the 22 sibling tools with an explicit fallback rule ('Usala solo cuando ninguna otra herramienta sirva'), so an agent knows exactly where this sits in the toolset.

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?

Gives both a negative condition (only when no other tool suffices) and a mandatory workflow: display the code to the user, wait for approval, then call with confirmed=true. That is explicit when-to-use plus when-not-to-use, leaving nothing to inference.

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