execute_python

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

Discloses persistent Python namespace across calls, isolated container, and output directory constraints. No annotations are provided, so the description carries the full burden; it does not cover error handling or resource limits but covers key behavioral traits.

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?

Information is front-loaded with the core action, followed by important details on namespace persistence and output rules. Some repetition from execute_r (same rules) is acceptable for completeness; not overly verbose.

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 tool's complexity (isolated container, persistent namespace, output constraints) and the presence of an output schema, the description covers essential aspects for correct usage, though it omits error handling or performance notes.

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?

Only one parameter 'code' with 0% schema coverage, but the name is self-explanatory. The description adds context about what to include (import packages, ensure output rules) and the environment, compensating for the lack of schema detail.

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 'Execute Python code in the isolated analysis container,' specifying the verb (execute) and resource (Python code). It distinguishes from execute_r by noting persistent namespace and referencing common output rules.

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?

Provides detailed output rules (aggregated results only, avoid per-sample CSVs, plot saving convention) and lists available packages. However, it does not explicitly state when to prefer Python over R or when not to use the tool.

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