eval_python

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

With no annotations, the description carries the full burden. It discloses that code runs in the app process, names the exposed context objects, and warns that it's debugging-only. However, it does not state the potential for arbitrary code execution side effects, state mutation, or crashes, which would be expected for a powerful eval tool.

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 three short sentences, front-loaded with the core purpose, followed by useful context and a clear warning. Every sentence contributes meaningful information with no waste.

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 one-parameter eval tool, the description is fairly complete: it states purpose, execution context, available objects, and a safety warning. The presence of an output schema covers return value expectations. It could be improved by noting whether the code is an expression or statement and whether execution is synchronous, but overall it is sufficient.

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?

The input schema lists only 'code' with a type of string and zero description coverage. The description does not explicitly describe the code parameter, but the tool name and the context line ('window, webview, api') imply that the code should be a Python snippet with access to those objects, adding some semantic value beyond the raw schema.

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 clearly states a specific action ('Evaluate Python') on a specific resource ('in the app process'), and the context line adds the available objects. This distinguishes it from siblings like eval_js (JavaScript) and call_api.

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 warning 'debugging only' provides an explicit when-not condition, and the context line indicates the execution environment. However, it does not explicitly mention alternatives such as eval_js for JavaScript evaluation, so it falls short of full guidance.

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