runtime_exec

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

Beyond the annotations, the description discloses that this is an unrestricted control environment, explicitly not a sandbox, and only available with a danger flag. It also reveals that state survives across calls via session_id. This materially augments the annotation hints and gives the agent a clear risk picture.

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?

Three purposeful sentences front-load the core purpose, then provide usage syntax, then the safety warning. There is no filler, and each sentence earns its place.

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 complex arbitrary-code execution tool with no output schema, the description covers the execution environment, persistence semantics, MCP invocation, structured return via result(value), and safety gating. Combined with the high-coverage input schema and annotations, an agent has enough to call it correctly.

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 100%, so the baseline is 3. The description adds meaningful context above the schema by documenting how to interact with MCP capabilities from code (await tools.<name> or await call) and by elaborating that variables/imports/helpers persist per session_id.

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: 'Execute model-generated Python in a persistent IPython/Jupyter kernel.' This clearly separates it from shell/process executors among the sibling tools, and the persistence detail adds a distinguishing scope.

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 implies when to use the tool—when persistent Python state and MCP capability access are needed—and gives in-kernel usage patterns. However, it never names alternatives or states when not to use it, so the routing guidance is left to inference.

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