execute_python

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

With no annotations, the description carries full responsibility and covers side effects, safety limits, and state ambiguity well: it warns "Not a sandbox," says raw code "can change the scene," may "access embedded Python filesystem/process capabilities," and notes a timed-out operation is "UNKNOWN" requiring reconcile_operation. This is exemplary disclosure for a dangerous execution 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 dense but each warning earns its place for a high-risk tool. Minor redundancy exists: "Static guard is not a sandbox" is followed by "Not a sandbox," which repeats the same point. Overall, critical safety information is front-loaded and readable.

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 there is no output schema and no annotations, the description covers the essential operational concerns: environment gating, side effects, filesystem/process capabilities, timeout ambiguity, and post-execution verification. It is slightly incomplete on what "modal-risk" means precisely and how to set the override, but it is otherwise sufficient for safe invocation.

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 compensate. It partly does: "import API modules and assign result" explains the intent of code, and "modal-risk calls require explicit override" implies the allow_potentially_modal parameter. However, it never names either parameter directly, leaving the agent to infer the mapping.

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?

"Execute reviewed Python" names a specific verb and resource, and "import API modules and assign result" clarifies what execution is for. It is not a tautology and the resource is clear, though it does not explicitly distinguish itself from sibling tools like preflight_python.

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?

"Look up docs/runtime first" and "MD_MCP_ALLOW_RAW_PYTHON=0 refuses this tool" provide useful context about prerequisites and environment gates. However, the description does not explicitly state when to use this tool versus alternatives or list any excluded cases.

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